agent_tool_risk_audit

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

The description declares the tool as 'Pure function, no I/O, no chaining,' which clearly communicates its safe, side-effect-free behavior. It also lists the types of risks it reports. Without annotations, this provides adequate transparency, though it could mention error handling.

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

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

The description is concise and well-structured: a one-line summary, bullet points for reported risks, and clear Args/Returns sections. Every sentence adds value without unnecessary repetition.

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

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

Given the tool's complexity and lack of output schema, the description fully explains inputs, expected formats, analysis capabilities, return type, and behavior (pure function). No gaps are apparent.

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

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

The schema only defines 'schema' as a generic object with no constraints. The description compensates by explaining that the parameter is 'A tool definition as a dict' and lists the acceptable formats (OpenAI function-calling, etc.), adding critical meaning beyond the schema.

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

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

The description clearly states the tool's purpose: 'Statically audit a single agent tool definition for schema-level risks.' It specifies the verb (audit), resource (agent tool definition), and scope (single, static). This distinguishes it from sibling tools like 'mcp_server_audit' which likely audits an entire server.

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

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

The description lists accepted input formats (OpenAI, Anthropic, MCP, bare JSON Schema) but does not explicitly guide when to use this tool versus alternatives like 'mcp_server_audit' or 'prompt_injection_audit'. Usage context is implied but not formalized.

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