Index of every page on this site: llms.txt
All skills
patricio0312rev avatar

/tool-function-schema-designer

@79ea6af
Run it yourself

Designs robust function/tool calling schemas for LLMs with JSON schemas, validation strategies, typed interfaces, and example calls. Use when implementing "function calling", "tool use", "LLM tools", or "agent actions".

Use this Skill: https://skilld.dev/gh/patricio0312rev/skills/tool-function-schema-designer

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈63 tokens for metadata: the name and description. ≈1.2k when used: this file.

Description uses 3.1% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈251 characters, or 3.1%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Tool/Function Schema Designer

Design robust tool schemas that LLMs can reliably invoke.

Function Schema Format

// OpenAI function calling format
const searchDocsTool = {
  type: "function",
  function: {
    name: "search_documentation",
    description:
      "Search through product documentation using semantic search. Use this when the user asks about features, how-tos, or troubleshooting.",
    parameters: {
      type: "object",
      properties: {
        query: {
          type: "string",
          description: "The search query, phrased as a question or keywords",
        },
        filters: {
          type: "object",
          properties: {
            category: {
              type: "string",
              enum: ["api", "guides", "tutorials", "troubleshooting"],
              description: "Filter by documentation category",
            },
            version: {
              type: "string",
              description: "Filter by product version (e.g., 'v2.0')",
            },
          },
        },
        max_results: {
          type: "integer",
          minimum: 1,
          maximum: 10,
          default: 5,
          description: "Maximum number of results to return",
        },
      },
      required: ["query"],
    },
  },
};

Typed Interfaces

// TypeScript types matching schema
interface SearchDocsParams {
  query: string;
  filters?: {
    category?: "api" | "guides" | "tutorials" | "troubleshooting";
    version?: string;
  };
  max_results?: number;
}

// Implementation
async function search_documentation(
  params: SearchDocsParams
): Promise<SearchResult[]> {
  const { query, filters = {}, max_results = 5 } = params;

  // Implementation
  return await vectorStore.search(query, {
    filter: filters,
    limit: max_results,
  });
}

Validation Strategy

import { z } from "zod";

// Zod schema for runtime validation
const searchDocsSchema = z.object({
  query: z.string().min(1, "Query cannot be empty"),
  filters: z
    .object({
      category: z
        .enum(["api", "guides", "tutorials", "troubleshooting"])
        .optional(),
      version: z.string().optional(),
    })
    .optional(),
  max_results: z.number().int().min(1).max(10).default(5),
});

// Validate before execution
function validateAndExecute(toolName: string, params: unknown) {
  const validated = searchDocsSchema.parse(params);
  return search_documentation(validated);
}

Tool Registry

export const TOOLS = {
  search_documentation: {
    schema: searchDocsTool,
    implementation: search_documentation,
    validator: searchDocsSchema,
  },
  create_ticket: {
    schema: createTicketTool,
    implementation: create_ticket,
    validator: createTicketSchema,
  },
  // ... more tools
};

// Execute tool safely
async function executeTool(name: string, params: unknown) {
  const tool = TOOLS[name];
  if (!tool) throw new Error(`Unknown tool: ${name}`);

  const validated = tool.validator.parse(params);
  return tool.implementation(validated);
}

Example Calls

// Example 1: Simple search
{
  "name": "search_documentation",
  "parameters": {
    "query": "How do I authenticate API requests?"
  }
}

// Example 2: With filters
{
  "name": "search_documentation",
  "parameters": {
    "query": "rate limiting",
    "filters": {
      "category": "api",
      "version": "v2.0"
    },
    "max_results": 3
  }
}

Error Handling

interface ToolResult {
  success: boolean;
  data?: any;
  error?: {
    code: string;
    message: string;
  };
}

async function safeExecuteTool(
  name: string,
  params: unknown
): Promise<ToolResult> {
  try {
    const data = await executeTool(name, params);
    return { success: true, data };
  } catch (error) {
    if (error instanceof z.ZodError) {
      return {
        success: false,
        error: {
          code: "VALIDATION_ERROR",
          message: `Invalid parameters: ${error.message}`,
        },
      };
    }
    return {
      success: false,
      error: {
        code: "EXECUTION_ERROR",
        message: error.message,
      },
    };
  }
}

Best Practices

  1. Clear descriptions: Explain when to use the tool
  2. Specific types: Use enums, ranges, patterns
  3. Sensible defaults: Reduce required parameters
  4. Validate rigorously: Don't trust LLM output
  5. Error messages: Help LLM correct mistakes
  6. Example calls: Show success cases
  7. Type safety: TypeScript interfaces

Output Checklist

  • JSON schema defined
  • TypeScript interface
  • Validation with Zod
  • Implementation function
  • Error handling
  • Example calls (3+)
  • Tool registry entry
  • Documentation

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 warning2mo5 checks · Risk SAFE
  • Gen Agent Trust Hub2mo

    This skill provides a set of templates and best practices for designing LLM tool schemas. It includes examples for JSON schemas, TypeScript interfaces, and runtime validation using Zod. No malicious patterns or security risks were detected.

  • Socket2mo

    No alerts

  • Snyk2mo

    Risk: LOW · No issues

  • Runlayer9mo

    1/1 file flagged

  • ZeroLeaks7mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at 79ea6af. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last month.

Dormantupdated 10 months ago

README badge

README badge for patricio0312rev/skills/tool-function-schema-designer