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

Annotations already declare idempotentHint=true, readOnlyHint=false and destructiveHint=false, so safety is largely covered. The description adds real value by explaining the mechanism behind idempotency ('makes a retry a no-op instead of a duplicate ask'), but says nothing about auth/permissions, any review or approval flow after submission, or limits on how often requests can be filed.

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?

A single dense sentence with three tight clauses, front-loaded on the purpose before the parameter notes. No filler, though the em-dash chaining is slightly run-on and could be split for scannability.

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 creation tool with no output schema, the description never says what comes back (a request id? a status?), nor what happens next (review, fulfillment, polling via my_tools). It covers inputs adequately but leaves the post-call lifecycle and return value entirely to inference.

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 0%, so the description must carry the burden, and it does: it clarifies that title/description are free-form author content, that desiredInputs/desiredOutputs are optional field lists the target endpoint should take/return, and that idempotencyKey is caller-supplied and must be stable per request. Only the trivial title/description field constraints (length limits) are left to 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?

States a specific verb and resource ('request a provider or job') and pins the scope to things 'the data API catalog does not cover yet', which cleanly separates it from catalog-reading siblings like search_catalog, discover, and catalog_overview. The endpoint equivalence (POST /v1/capability-requests) gives an unambiguous anchor.

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 'does not cover yet' condition is an explicit when-to-use trigger that implies the reader should first check the catalog tools. It stops short of naming the specific alternatives (search_catalog/discover) or stating when-not to file a request (e.g., duplicates), so it falls just 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.