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

Good context beyond annotations: mentions it starts the job and waits, with wait_seconds, and reuses finished transcripts. Annotations cover idempotency (idempotentHint=true) and safety. However, doesn't detail rate limits, auth, or error conditions, but idempotency is already declared.

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?

Two concise sentences, front-loaded with the core action, then important behavioral details. Every part is useful.

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?

Given no output schema, the description covers key behaviors: async handling via task_id, reuse of finished transcripts, and background First Pass trigger. Missing details on return format or error handling, but sufficient for correct invocation.

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 33%, so description adds value by explaining wait_seconds behavior ('waits up to wait_seconds') and that a task_id is returned for polling. language is documented in schema. audio_file_id is implied but not explicitly described.

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+resource: 'Word-level transcript (Whisper) for an audio_file_id.' Clearly distinguishes from cast_get_transcript and cast_first_pass by describing the generation action vs retrieval.

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?

Explains when to use it: 'if it is still running you get a task_id to poll with cast_get_task' and 'A finished transcript is reused, not re-run.' This gives clear context and routing to alternatives.

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