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

Annotations already mark readOnly=true and destructive=false; the description reinforces with 'Read-only' and adds significant non-obvious behavior: API key requirement, credit billing (≈3 per 1,000 words, min 5, repeat calls billed), error cases that avoid charges, and a 5 req/10s rate limit. No contradiction with annotations.

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 yet information-dense; the first sentence states core purpose, the second gives usage guidance, and subsequent sentences handle cost, errors, and rate limits – all non-redundant. Length is justified by the billing and rate-limit caveats.

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 tool with one documented parameter, an output schema, and readOnly annotations, the description covers all operational essentials: prerequisites (API key), cost model, failure conditions, and throttling. There are no major behavioral gaps.

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% and the single 'video' parameter is well documented in the schema (ID or URL forms). The description adds no extra parameter-level meaning, so the baseline of 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?

The description opens with a specific verb and resource ('Get a cleaned-up transcript') and enumerates concrete transformations (punctuation, filler removal, paragraphs, name fixes). It explicitly distinguishes from get_transcript, making its purpose unmistakable.

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 states 'Use when raw captions are too messy to read or quote' and names the explicit alternative 'for a plain transcript use get_transcript'. It also lists error conditions (human-uploaded captions, over ~7,000 words), giving clear guidance on when not to use it.

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