rest_describe

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

No annotations are provided, so the description carries full burden. It discloses that the tool returns response structure and TypeScript interfaces without the full body, which is key behavior. It also states the base URL and that the endpoint is resolved to that base. However, it doesn't disclose potential side effects (e.g., does it modify data? It's HTTP request, could be destructive for POST/PUT/DELETE) or state that no authentication is handled (since rest_set_token exists). The description implies a read-only analysis but doesn't explicitly say it doesn't mutate data, which is a slight gap. But given the context, it's reasonably transparent about what it returns and how it works.

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 somewhat long but well-structured: it starts with the main purpose, then PRIMARY PURPOSE, then base URL, then nested context resolution guidance. However, the "AUTONOMOUS CONTEXT RESOLUTION" section is quite verbose with numbered steps and detail. It could be trimmed, but each sentence adds value—especially the guidance for dynamic values. It is front-loaded with purpose and key behavior, so it's appropriately structured despite being long. Slight deduct for verbosity.

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?

This is a complex tool with 6 parameters, no annotations, no output schema. The description covers all necessary aspects: purpose, usage guidance, parameter resolution, and expected output (TypeScript interfaces). It includes a base URL and explains how to handle dynamic parameters. For the tool's complexity, the description is complete and provides enough information for an AI to invoke it correctly. The lack of output schema is compensated by explaining what the tool returns. Overall, it's a thorough description that leaves little to guess.

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?

Schema description coverage is 100%, so each parameter has a basic description. The description adds significant meaning beyond the schema: it explains how to resolve parameters in context (e.g., "Path params (:id, :slug) — find actual values in component data..."), and explains the default for typeName ("Root interface name... default: "ApiResponse"" which is also in schema but the description emphasizes the default). The description also clarifies that endpoint is path only and resolved to base URL, which adds context beyond the schema's description. This elevates the parameter semantics beyond baseline.

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: "Execute an HTTP request and return the response structure (keys, types, array lengths) AND generated TypeScript interfaces — without the full body." It uses a specific verb (execute) and resource (HTTP request), and distinguishes itself from siblings by highlighting the generated TypeScript interfaces and its focus on structure, not full body. The purpose is further reinforced with "PRIMARY PURPOSE" and "Always present the generated TypeScript interfaces without being asked".

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 provides explicit guidance on when to use this tool: "Ideal for large responses." and implies it is for API response analysis. It also gives detailed instructions on how to resolve parameters when the endpoint comes from code analysis (feature-port, migration, etc.), including steps to find path params, query params, request body, and fallback to representative test values. This is comprehensive and distinguishes it from siblings by focusing on type derivation rather than raw request execution.

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