Create Captions

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

Annotations already declare destructiveHint=true, readOnlyHint=false, openWorldHint=true, and non-idempotency. The description adds real value beyond that: the exact permission scope, the delegation-token caveat, the confirm=true gate, and side effects (sharing access, notifying people, provider charges). It stops short of describing what happens to pre-existing captions for the same language.

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?

The purpose sentence is front-loaded and the requirements are separated into scannable blocks. The permission section is long but carries actionable content rather than 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?

For a non-idempotent mutation with 7 parameters and no output schema, the description covers auth, the confirm gate, and side-effect exposure well. The main omission is the effect on existing captions for the same media/language and any response expectation.

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 100%, so the schema already documents media_hashed_id, caption_file, language, payload, and payload_file. The description restates only the SRT input form and adds no format or precedence detail (e.g., payload vs. body flags, caption_file string vs. file upload) beyond what the schema provides.

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 first sentence gives a specific verb (adds), resource (captions), and target (a specified media), plus the input form (SRT file or its contents). It is clear, though it does not explicitly differentiate from sibling caption mutators like update_captions or edit_captions_text.

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?

Usage context is implied by the permission and confirm=true requirements, which tell the agent this is a gated write. However, it never states when to choose this tool over update_captions, edit_captions_text, or purchase_captions, all of which live in the same sibling cluster.

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