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

Beyond the readOnlyHint annotation, the description discloses credit charging (about 3 per 1,000 words, minimum 5), repeat calls are charged, requires API key, rate limit of 5 requests per 10 seconds, and error cases that do not charge. This is rich behavioral context.

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 a single, well-organized paragraph. Every sentence adds value: purpose, use case, alternative, read-only, credits, errors, and rate limit—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 the tool's complexity, the description explains expected behavior (cleaning), costs, error conditions, and rate limits. With an output schema present, return format is covered, making the description complete for selection and invocation.

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?

The schema already fully describes the single 'video' parameter with ID/URL examples (100% coverage). The description adds no additional parameter semantics, so it meets the baseline of 3.

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 uses a specific verb 'Get a cleaned-up transcript' and details the exact transformations (punctuation, capitalisation, filler removal). It distinguishes itself from sibling get_transcript by noting that it polishes auto-generated captions.

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?

It explicitly states when to use ('Use when raw captions are too messy to read or quote') and directs to an alternative ('for a plain transcript use get_transcript'). It also excludes cases that error out (human-uploaded captions, transcripts over ~7,000 words).

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