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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds useful format context ('one line per cue', English default for secondary) but doesn't say whether the result is returned inline as text or as a path/URL — a real behavioral gap for a download-style 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 core action, then format, then the key parameter caveat. No wasted text.

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?

No output schema exists, and the description gives the essential return characteristic (one line per cue) plus the track default. The only missing piece for full completeness is whether the response is raw file content or a handle/URL.

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%, so the baseline is 3, but the description adds meaning beyond the schema: it clarifies that "secondary" is the translated track and that English is the default, which the schema's enum description does not state. jobId is left to 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?

States a specific verb ('Return') and resource ('subtitle file for a finished job') with the format (SRT) implied by the name and 'one line per cue'. It's clearly distinct from list_cues or get_job, though it never explicitly names an alternative.

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 phrase 'for a finished job' implies a precondition, and it helpfully points to track="secondary" for the translated track. However, it doesn't say what to do if the job isn't finished or direct the agent to a sibling for the non-file case; usage is implied rather than spelled out.

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