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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the read-only nature is covered. The description adds value by clarifying that no subtitle content is downloaded and by exposing a credit-efficiency nuance: get_transcript with metadata returns both for one credit, whereas this tool and get_transcript would be two calls. This is genuinely useful beyond the structured hints.

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 with a strong front-loaded purpose, followed by a quick usage rule and a cost rationale. It is slightly longer than strictly necessary, but every sentence provides distinct value, 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 a single well-documented parameter and an existing output schema, the description covers everything an agent needs: what is returned, what is excluded, when to use an alternative, and the cost trade-off. Nothing crucial is missing.

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%: the id parameter is documented as 'YouTube video id or URL'. The description implies it targets a single video and includes fields like title and views, but it does not add meaning beyond the schema. The baseline of 3 is appropriate given the schema is already complete.

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 opens with a specific verb ('get metadata' for one YouTube video), enumerates the exact fields returned (title, channel, duration, views, thumbnails), and adds a constraint ('WITHOUT downloading the subtitles'). It is unmistakably distinct from the sibling get_transcript, which fetches the subtitles themselves.

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 provides an explicit condition: 'Use it only when the transcript itself is not wanted.' It also names the alternative (get_transcript with video_metadata=true) and explains why that route is better when the transcript is needed anyway. This is model guidance on when to choose this tool over a sibling.

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