YouTube Transcript API

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

Beyond the readOnlyHint annotation, the description adds useful behavioral context: cost differences between live reads and cache hits, the single-object return shape, and the public-data-only scope. It does not over-promise on return size or completeness, though it omits edge cases like videos without transcripts.

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 description is compact, front-loaded with the core purpose, and each sentence adds distinct value: output type, field naming behavior, cost, data scope, and read-only nature. There is 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?

Given no output schema, the description adequately conveys what the agent should expect: a single object representing the full transcript with timed segments. Combined with the complete parameter schema and annotations, this is enough for correct tool selection and invocation, though explicit field names are not provided.

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% for both parameters, so the schema already documents semantics. The description does not elaborate on the parameters, but the baseline of 3 applies because no additional explanation is necessary for an agent to use them correctly.

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 clearly identifies the resource (full spoken transcript of a public YouTube video) and the output shape (one object with timed segments). This unambiguously distinguishes it from sibling tools like youtube_stats or youtube_videos.

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 description makes clear the tool is for fetching spoken transcript content and notes it is limited to public data, which helps agents avoid using it for private or login-walled videos. It does not explicitly name alternatives, but the sibling set and resource clarity make the intended use obvious.

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