Correct transcript words

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

With no annotations, the description carries full weight and does well: it discloses the return shape { ok, flagId, rerendered, hint }, which implies a review flag is created, and explains how to reverse the change. Missing are permission requirements, whether the source transcript or existing renders are otherwise altered, and what `hint` means.

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 compact clauses: the effect first, the constraint second, the return and undo last. Nothing is padded and the most important information is front-loaded.

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 mutation tool with no annotations and no output schema, the description supplies both the response fields and the reversal path, which is exactly the gap structured data leaves. It could go one step further on permission or review-workflow impact, but an agent can call it correctly.

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%, so the baseline is high; the description still adds meaning by tying startSec/endSec to "the words spoken" and clarifying that text is what the captions should read, reinforcing the whole-word constraint. No redundant restatement.

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?

Names the concrete effect (captions show "text" instead of the spoken words) plus the exact span parameters, so it is unmistakable what resource is mutated. The contrast with review_transcript_flags (undo path) and add_transcript_cut clarifies its niche.

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?

Gives a motivating case ("a misheard name, say"), a hard precondition ("the span must cover whole words"), and an explicit undo route via review_transcript_flags with status rejected. It stops short of saying when to prefer add_transcript_cut or list/flags-review workflows instead.

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