write_api

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

Annotations already declare destructiveHint, openWorldHint and non-idempotency, but the description adds context annotations cannot: the operation mutates production data, and dryRun performs validation without any network call. It does not say what a successful call returns or how partial failures surface, leaving a gap for a destructive no-output-schema tool.

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 short sentences, front-loaded with the action and the production-impact warning, then the dryRun escape hatch, then the hard limitation. No sentence is filler.

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 five-parameter, nested-object, destructive tool with no output schema, it covers safety and validation but omits the response shape and any guidance on resolving path/query values. An agent knows it is dangerous but not what it gets back.

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 60%: operationId and body are described there, but path and query are undocumented in both places. The description's one real contribution is the dryRun semantic (validates without a network call), which the bare boolean in the schema does not convey; it says nothing about operationId sourcing or path/query usage.

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 class plus resource and scope: 'Execute a schema-validated official Apple POST/PATCH/DELETE operation.' The word 'official' and the schema-validated framing distinguish it from the read-only sibling read_api and from the discovery tools search_api_operations/get_api_operation.

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?

Gives a real precondition ('only use within the user's authorized scope'), a validation path via dryRun, and one explicit exclusion ('Cannot create a new app record: Apple requires its website'). It stops short of steering the agent to dedicated siblings such as update_app_description or set_iap_price when those exist for a specific mutation.

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