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

Goes well beyond the annotations: it explains whole-word/consecutive matching, that replace inherits the time span of the replaced words, that every caption and search updates as a side effect, that the transcript is asset-scoped (hence no branchId), and that the operation is atomic ('All edits apply or none do'). These are non-obvious mutation semantics that the readOnlyHint/destructiveHint flags cannot convey.

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?

Front-loads the purpose in the first sentence and packs dense, useful detail into six short sentences. Every sentence carries weight; a slight tightening is possible, but nothing is redundant 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?

With no output schema and no annotation support for mutation semantics, the description covers the essentials an agent needs: atomicity, side effects on captions/searches, asset-vs-version scoping, and the read-before-edit prerequisite. Nothing material is missing for a correct call.

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 only 33%, so the description must compensate, and it does: it defines what `find` and `replace` mean semantically, that replacement takes over the time span, and it explains why `branchId` is absent. It does not restate the nearSeconds disambiguation rule, but the added meaning on the edit objects is substantial.

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 and resource ('Correct words in a completed transcript') and immediately distinguishes itself from siblings by noting it 'Does not transcribe again' (vs transcribe_asset) and by pointing to read_transcript. An agent can separate this from read/patch component or film tools without opening the schema.

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 clear precondition workflow: 'Read the words with read_transcript first,' and rules out re-transcription. It stops short of explicitly naming transcribe_asset as the alternative for creating rather than correcting a transcript, so it is clear context without formal when/when-not routing.

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