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

Annotations already declare a safe read, and the description adds real behavioral context on top: the four possible statuses, the paid-reservation failure mode with a recovery action, the 24 h signed wordsUrl expiry, and the 15-minute limit on includeWords. This is exactly the operational detail annotations cannot carry.

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?

Front-loaded with the action and status set, then the success payload, then the parameter tradeoffs. Every clause carries unique information; no restatement of the name or 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?

Even though an output schema exists, the description covers the async lifecycle, the failure/payment branch, and the context-budget flags an agent must reason about. Nothing needed to call this correctly 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 coverage is 75% and two flags (includeWords, includeText) carry no schema description, but the description compensates: it explains what each flag does, the 15-minute inlining limit, and that disabling includeText/includeSegments keeps long transcripts out of context. It also clarifies transcriptionId is the jobId from transcribe_media.

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 ('Poll a transcription by its jobId') plus the exact scope of what it returns (status, text, segments, wordsUrl). Clearly distinct from the sibling create-side tool transcribe_media and from list_transcriptions.

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 the polling loop well, including the non-obvious payment_required branch and the 'top up creditsDue and poll again' remediation. It never names an alternative tool (e.g. list_transcriptions) or says when not to use it, so it stops 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.