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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The word 'finished' usefully implies that only completed jobs yield a transcript, but the description doesn't say what happens for pending/failed jobs, nor how large a transcript can be or whether it is truncated — gaps that matter for a retrieval 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?

A single front-loaded sentence with the resource and its variations, and no filler. Every clause carries information an agent can act on.

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 two-parameter read tool with no output schema and annotations that cover the safety profile, the description is close to sufficient. It falls short on what happens when the job isn't finished and on any error or size behavior, which an agent may need when a call fails.

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 100%, with both jobId provenance and the format enum fully documented in the schema, so the baseline is 3. The description merely restates the format options ('plain text, timestamped text or SRT') without adding any semantics beyond the enum values.

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 states a specific verb and resource ('Returns a finished transcript') and enumerates the three output formats, so the agent knows exactly what it gets back. It doesn't explicitly contrast itself with list_transcripts or transcribe_url, so the sibling differentiation is only implicit in the word 'finished'.

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?

There is no when-to-use or when-not-to-use guidance in the description itself; the only routing hint ('Job ID from transcribe_url or list_transcripts') lives in the schema, not the description. The agent must infer that this tool is for retrieving an already-completed job rather than starting or enumerating one.

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