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

Annotations already declare readOnlyHint=false, idempotentHint=false and destructiveHint=false, so the safety profile is partly covered. The description adds genuinely non-structured context — billing is per input character and word timing is left untouched — but says nothing about auth needs, rate limits, or how much the text itself may change.

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 short sentences, each carrying a distinct fact (action, scope limit, cost model), with the core contract front-loaded and 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?

The core text contract and billing model are covered for a 4-parameter mutation-style tool with no output schema. However, with 3 of 4 parameters undocumented and no explanation of what 'correct' actually alters or what comes back, an agent can invoke it but not fully predict the result.

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 only 25% (request_id is the sole documented field), yet the description describes no parameters at all. glossary and language are left completely undefined in both schema and description, so the description fails to compensate for the coverage gap.

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+resource ('Correct caption text') and constrains the contract ('preserving caption count and order'), which immediately separates it from translate_captions and transcribe_audio. It stops short of naming a sibling explicitly, so an agent must still infer routing from the name alone.

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?

There is no explicit when-to-use guidance and no named alternative. 'Does not realign word timing' implies a boundary against timing/alignment workflows, but it is a scope constraint rather than a comparison with the sibling tools an agent must choose between.

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