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

Goes well beyond the readOnly/openWorld/idempotent annotations by disclosing the cost model (1 credit for the first page, later pages free for 30 minutes), the pagination contract (the result ends with the offset to pass next), and the error/refund behavior for captionless videos. These are exactly the operational facts an agent needs.

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 sentences, front-loaded with what is returned and in what formats, then paging, then cost. No filler; each sentence carries distinct operational information.

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 return-value burden and does so: it describes the Markdown/text/SRT/VTT shapes and the trailing offset for continuation. Combined with cost and error disclosure, an agent has everything needed to call and continue correctly.

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 video, format, offset, languages, and max_chars. The description largely restates the format variants and adds paging intent for offset, but says nothing about languages selection or the max_chars cap. Baseline 3 is appropriate.

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 and resource (returns the captions of a public YouTube video) and names the concrete output forms. It is unambiguously distinct from siblings like get_video_details or get_comments, which return metadata and comment data rather than caption 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?

Gives clear context for when this applies: caption retrieval with selectable format, paged output, and an explicit failure case (no captions -> error, no charge). It does not name a sibling alternative or describe when NOT to use it, so it stops short of a 5.

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