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

Annotations already declare readOnly/idempotent/non-destructive, so the safety bar is low; the description still adds real value by disclosing the ownership requirement ('owned' document), that no charge or transcription is incurred, and the output nature (sidecar text vs. burned-in video). The 'save under filename' clause is confusing because no filename parameter exists, which keeps this from a 5.

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 tightly written sentences with the core purpose front-loaded and no filler. The middle sentence about saving under 'filename' is slightly wasteful and potentially misleading since the schema exposes no such parameter.

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?

With no output schema, the description compensates by stating exactly what is returned (complete SRT/WebVTT text) and what it is not. It covers ownership, cost, and the burn-in alternative. Only the documentId/revision semantics and the stray filename reference remain under-specified for a 3-required-param tool.

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 description coverage is 0%, so the description must carry the param burden. It partially does: 'SRT or WebVTT' maps to the format enum, 'owned' implies the ownership constraint on documentId, and 'exact document revision' clarifies the revision selector. It does not explain documentId syntax or why a specific revision integer is required, leaving a real gap.

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 complete SRT or WebVTT text') and resource (an owned document revision), and explicitly contrasts itself with the burn-in path ('use prepare_subtitle_export for burn-in'). An agent can distinguish this from prepare_subtitle_export without opening any schema.

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?

Clearly sets context ('This produces a caption sidecar, not a captioned video') and names the alternative tool for the other case (burn-in). It also flags that the export is free ('without charge or new transcription'), which is decision-relevant. It stops short of a full explicit when/when-not rule set, but the routing is unambiguous.

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