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

Annotations already declare idempotentHint=true and destructiveHint=true, so the burden is lighter, yet the description still adds real context: retry behavior ('avoids duplicate captions on identical retries'), that the full recording is preserved, and that no-speech is a legitimate success rather than a failure. It stops short of saying which existing editable captions are overwritten or what authorizations are needed, so it is not a 5.

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 tight sentences, with the core action front-loaded and each clause carrying distinct information (source, retry/idempotency behavior, precondition, edge case). No filler or repetition.

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?

An output schema exists so return values need not be described, and the annotations cover safety and idempotency. The description supplies the prerequisite and the no-speech success state, leaving only minor gaps around overwrite scope and parameter mapping.

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?

Only half the parameters carry schema descriptions, and those present just say 'UUID string'. The description adds indirect meaning for idempotencyKey ('identical retries') and projectId ('project captions'), but it never clarifies the assetId-vs-projectId relationship or the source-selection semantics, so it only partially compensates 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?

The description pairs a specific verb and resource ('Restore editable project captions from the selected source's completed canonical transcript'), which is clearly distinct from siblings like captions_words_list or media_transcript_get. It does not explicitly name a sibling to disambiguate against, but the resource is precise enough for an agent to select it.

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 states a meaningful precondition ('Requires source transcription first') and defines an edge outcome ('no-speech is an explicit successful state'), which tells the agent when the call is valid. However, it never names an alternative tool or a when-not condition, so routing against e.g. captions_words_correct or captions_look_apply is left to inference.

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