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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds genuinely new constraint context beyond them: only public videos are accessible, and no video/audio is fetched, only text captions. It stops short of describing failure modes (private videos, missing caption tracks) or rate limits.

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?

Two short sentences, output scope front-loaded, no redundant restatement of the title or schema. Every clause carries 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?

For a two-parameter read tool with full schema coverage and rich annotations, the description is nearly sufficient, and it even gestures at the return shape ('timestamped plain text') despite no output schema. Only error/fallback behavior when no captions exist is unaddressed.

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 both parameters (url with its video-id form, lang with its fallback behavior) are already fully documented in the schema. The description adds no parameter-level detail beyond the 'public' qualifier, so the baseline 3 applies.

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 (Read) and resource (public YouTube captions) plus the output form (timestamped plain text), which is far more precise than the sibling calculators. It does not name a sibling alternative, but the 'captions only, no video or audio' clause effectively separates it from media-download or page_to_markdown tools.

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?

'Read public YouTube captions' implies the applicable case (a YouTube URL with public captions) and the exclusion of video/audio, but there is no explicit when-to-use statement or routing to alternatives such as page_to_markdown for non-YouTube pages. Usage is inferable rather than stated.

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