Get transcription result

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

Annotations indicate read-only, idempotent, non-destructive behavior. Beyond that, the description adds polling behavior details (wait_ms and polling loop) and lists the exact data returned. No contradictions.

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 sentences, first covers purpose and fields, second covers polling guidance. No redundant words, front-loaded with key information.

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 simple fetch tool with two parameters and no output schema, the description adequately covers purpose, return data, and polling behavior. Minor gaps like error handling are acceptable given its simplicity.

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?

With 50% schema coverage, the description clarifies 'job_id' as the transcription identifier (schema only has minLength) and explains 'wait_ms' as a long-poll mechanism (schema provides defaults/max). This adds meaning beyond 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?

The description explicitly states 'Fetch a transcription by job_id' and lists the return fields, making the purpose clear and specific. It distinguishes from sibling tools like 'list_transcriptions' and 'search_transcript' by being a direct fetch by ID.

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 description gives guidance on using 'wait_ms' for long-polling and implies polling until status is 'done'. It does not explicitly compare to alternatives but provides clear usage context.

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