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

Annotations only declare that this is a non-read-only, non-destructive, non-idempotent, open-world call; the description goes well beyond that by disclosing the side effects (a new request ID, a new recipe run for structured extraction, source preserved for audit), the required scope 'scrape:write', and the exact error code emitted for an unsupported request type. The return-shape note ({ok,status,data,meta} vs {ok:false,status,error}) is also behavior the annotations cannot express.

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?

Four sentences, each carrying a distinct payload: what it does, what it creates, the exception path with its error code and alternative, and the auth/return contract. The core action and the destructive-vs-audit nuance are front-loaded, and nothing is restated from the title or schema.

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?

With no output schema, the description compensates by describing both success and failure response envelopes, and it covers the auth requirement and the one refusal case an agent will realistically hit. For a two-parameter mutation tool, nothing needed to call it correctly or interpret the result 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 description coverage is 100%, so both the id (UUID of request or batch) and the idempotency_key (replay semantics, 409 IDEMPOTENCY_CONFLICT) are already fully documented in the schema. The description only echoes 'the path id' and mentions idempotency keys in the context of the alternative workflow, adding little meaning beyond the structured fields. Baseline 3 is appropriate here.

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 opens with a specific verb and resource ('Retries the failed request identified by the path id') and immediately clarifies the resulting semantics: a new request ID is created while the failed source is preserved for audit. That distinguishes it from data_create_request (which has no source request) and from data_get_request/data_cancel_request without needing to open any schema.

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?

It states the precondition (the target must be a failed request identified by id) and gives an explicit exclusion with a redirect: website task/tool requests are refused with WEBSITE_TOOL_RETRY_REQUIRES_NEW_REQUEST and must instead be submitted as a new task/tool request with a fresh idempotency key. That is a when-to-use / when-not-to-use / do-this-instead triple, which is the strongest form of routing guidance.

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