Call any API endpoint

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

Discloses authentication, path relativity, read-only mode blocking non-GET, and return format including error envelopes. Does not discuss side effects of mutations, rate limits, or authorization scopes. Without annotations, more depth on side effects would be beneficial.

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?

Three sentences, front-loaded with purpose, example, and key behavior. Every sentence adds value with no redundancy. Highly efficient.

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?

Covers return structure, path usage, and read-only behavior. Lacks details on error handling specifics, authentication mechanism, and potential side effects. For a generic tool, it is adequate but not thorough.

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?

Adds context for path (relative to base, examples) and method (enum already clear). For query and body, description only says 'JSON body' and 'object' but no additional constraints or format details beyond schema. Schema coverage is 50%, so description partially compensates.

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?

Description clearly states it performs generic authenticated requests to any backend route, with examples. It mentions using list_endpoints to discover paths, which implies differentiation from specific tools, but does not explicitly distinguish from siblings like get_project or list_projects.

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?

Provides guidance on when to use: for general API access, and references list_endpoints for path discovery. Mentions blocking of non-GET when MCP_READONLY is set, which is a usage constraint. No explicit when-not or alternatives, but the generic nature makes it clear.

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