Skip to main content
Glama

lint_tool_definition

Sanity-check a tool definition for common mistakes that hurt LLM tool-use accuracy: missing or vague descriptions, omitted required fields, schema fields without descriptions, and non-snake_case names.

Instructions

Sanity-check a tool definition for common mistakes that hurt LLM tool-use accuracy: missing description, vague description, no required fields, schema fields without descriptions, non-snake_case names.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
toolYesA tool definition: { name, description, inputSchema }.

Implementation Reference

  • The 'lintToolDefinitionTool' function that executes the linting logic: checks tool definition for missing name, non-snake_case name, missing/short/vague description, missing inputSchema, missing properties, fields without descriptions, and missing required fields.
    function lintToolDefinitionTool(input: { tool: any }) {
      const t = input.tool ?? {};
      const warnings: string[] = [];
    
      if (!t.name) {
        warnings.push('missing name');
      } else if (!/^[a-z][a-z0-9_]*$/.test(t.name)) {
        warnings.push(`name "${t.name}" should be snake_case (lowercase, digits, underscores; starts with a letter)`);
      }
    
      if (!t.description) {
        warnings.push('missing description — LLMs rely on this to pick the right tool');
      } else if (t.description.length < 20) {
        warnings.push('description is very short — consider expanding what the tool does, when to use it, and any preconditions');
      } else if (/^(does stuff|misc|util|helper)$/i.test(t.description.trim())) {
        warnings.push('description is too vague to be useful');
      }
    
      const schema = t.inputSchema;
      if (!schema) {
        warnings.push('missing inputSchema — tool calls will not be validated');
      } else {
        if (schema.type !== 'object') {
          warnings.push('inputSchema.type should be "object" for MCP tool inputs');
        }
        if (!schema.properties || Object.keys(schema.properties).length === 0) {
          warnings.push('inputSchema has no properties — accepts arbitrary input');
        } else {
          for (const [field, spec] of Object.entries(schema.properties as Record<string, any>)) {
            if (!spec || typeof spec !== 'object') continue;
            if (!spec.description) {
              warnings.push(`schema.${field}: missing field description (LLMs use this to pick correct values)`);
            }
          }
        }
        if (!schema.required || (Array.isArray(schema.required) && schema.required.length === 0)) {
          warnings.push('inputSchema has no required fields — every call is "valid" and validation cannot help');
        }
      }
    
      return {
        content: [
          {
            type: 'text',
            text: JSON.stringify({ ok: warnings.length === 0, warnings }, null, 2),
          },
        ],
      };
    }
  • Input schema for 'lint_tool_definition' tool: expects a 'tool' object with name, description, inputSchema fields, where only name is required.
    {
      name: 'lint_tool_definition',
      description:
        'Sanity-check a tool definition for common mistakes that hurt LLM tool-use accuracy: missing description, vague description, no required fields, schema fields without descriptions, non-snake_case names.',
      inputSchema: {
        type: 'object',
        properties: {
          tool: {
            type: 'object',
            description: 'A tool definition: { name, description, inputSchema }.',
            properties: {
              name: { type: 'string' },
              description: { type: 'string' },
              inputSchema: { type: 'object' },
            },
            required: ['name'],
          },
        },
        required: ['tool'],
      },
  • src/server.ts:53-109 (registration)
    Tool catalog array (TOOLS) that registers 'lint_tool_definition' along with other tools, used by ListToolsRequestSchema handler.
    const TOOLS = [
      {
        name: 'validate_tool_args',
        description:
          'Validate a tool-call args object against a small shape spec. Returns { valid, error?, retry_hint? } where retry_hint is a ready-to-send LLM feedback message describing exactly what was wrong.',
        inputSchema: {
          type: 'object',
          properties: {
            tool_name: {
              type: 'string',
              description: 'Name of the tool being called (surfaces in retry_hint).',
            },
            args: {
              type: 'object',
              description: 'The args object the LLM wants to pass.',
            },
            shape: SHAPE_SCHEMA,
          },
          required: ['tool_name', 'args', 'shape'],
        },
      },
      {
        name: 'lint_tool_definition',
        description:
          'Sanity-check a tool definition for common mistakes that hurt LLM tool-use accuracy: missing description, vague description, no required fields, schema fields without descriptions, non-snake_case names.',
        inputSchema: {
          type: 'object',
          properties: {
            tool: {
              type: 'object',
              description: 'A tool definition: { name, description, inputSchema }.',
              properties: {
                name: { type: 'string' },
                description: { type: 'string' },
                inputSchema: { type: 'object' },
              },
              required: ['name'],
            },
          },
          required: ['tool'],
        },
      },
      {
        name: 'generate_retry_message',
        description:
          'Given a tool name, validation error, and attempted args, build the canonical LLM-facing retry feedback message. Uses agentvet\'s ToolArgError.toLLMFeedback() formatting so the wording matches what runtime callers see.',
        inputSchema: {
          type: 'object',
          properties: {
            tool_name: { type: 'string' },
            validation_error: { type: 'string' },
            attempted_args: { type: 'object' },
          },
          required: ['tool_name', 'validation_error', 'attempted_args'],
        },
      },
    ] as const;
  • src/server.ts:123-124 (registration)
    Dispatch in CallToolRequestSchema handler: case matching 'lint_tool_definition' calling lintToolDefinitionTool.
    case 'lint_tool_definition':
      return lintToolDefinitionTool(args as { tool: any });
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. It describes the analysis but does not explicitly state it is non-destructive or disclose output format. The behavior is implied but not fully transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence with no unnecessary words. It efficiently communicates the tool's purpose and checks.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema is provided, and the description does not explain the return value (e.g., a list of issues). For a linting tool, this is a gap that reduces completeness for an AI agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the parameter 'tool' has a description explaining its structure. The description adds context about what to include, aiding correct invocation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly specifies the verb 'Sanity-check' and the resource 'tool definition', listing specific checks. It distinguishes from sibling tools (generate_retry_message, validate_tool_args) by its focus on definition quality.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for checking tool definitions, but lacks explicit when-to-use or when-not-to-use guidance. However, the context of sibling tools helps differentiate usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/MukundaKatta/agentvet-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server