Diagnose a request

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

Annotations already declare readOnlyHint=true and openWorldHint=false; the description reinforces this with 'Only reads the text; never sends the request', which is the key behavioral guarantee an agent needs before pasting a request containing credentials. It also discloses a cost trait ('Uses one request'), implying quota consumption, which is not in the annotations. It stops short of describing output shape or limits on ambiguous input.

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 tight sentences, front-loaded with the action and input form, then the diagnostic coverage, then the safety and cost notes. The parenthetical failure list is long but each item adds discriminating information about what the tool can catch.

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?

For a 3-parameter read-only tool with no output schema, the description covers input forms, diagnostic scope, safety, and cost. It implicitly describes the return value ('explains what is wrong ... and how to fix it'). Minor gaps remain around auth requirements and behavior on malformed input, but nothing an agent needs to invoke it correctly is missing.

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 coverage is 67%, and the description compensates by clarifying all three inputs: the request can be a curl command, a URL, or a 'GET /v2/...' line, and status/response are optional add-ons. The schema descriptions for request and response are extended with accepted formats rather than merely repeated.

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?

States a specific verb (diagnose) and resource (a failing WorkoutX request), and enumerates the exact failure classes it detects (wrong host, key in URL, missing header, v1 id, plan gate, rate limit, quota). This is clearly distinguishable from siblings like get_endpoint_reference or check_api_key, which do not diagnose a concrete failing call.

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 trigger is explicit: paste a failing request, optionally with status and response body. It tells the agent what input forms are accepted (curl, URL, "GET /v2/..."). It does not explicitly name when to prefer a sibling such as get_endpoint_reference or check_api_key instead, so it falls short of a 5.

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