Show Captions

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so safety is covered structurally. The description adds substantive behavior beyond that: the required API token permission, the delegation scope for team-member tokens, and that include_speakers is ignored outside TXT responses.

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 core action, then format options, then permissions in a headed block. Sentences are compact and each carries distinct information with no 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?

With no output schema, the description carries the burden of explaining return shape, and it does so adequately by naming the four formats and the segment/diarized_segments options. Only minor gaps remain, such as pagination or size limits for large transcripts.

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%, which sets the baseline at 3. The description adds meaning the schema lacks, specifically the mechanism for selecting output format via extensions or Accept headers, a format control that has no corresponding entry in the input 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 states a specific verb and resource ('Returns a media's captions') plus scope ('in the specified language'). It is clear what the tool does, though it never names or contrasts itself with near siblings such as list_captions, list_all_captions, or get_media_extended_audio_description.

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?

It explains how to request formats (file extensions or Accept headers) and that is the default, which gives real invocation context. However, it offers no when-to-use guidance relative to the many other caption/transcript tools in the sibling list, so alternative selection is left to inference.

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