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

Annotations already declare write/idempotent/non-destructive, but the description adds material context: app recording validation, durable operation, provider admission and daily spend guards, setup cost in the first Film quote with no customer-credit debit, retry reconciliation, and refusal before provider work for unconfigured cloning. This goes well beyond the annotation set and helps set expectations.

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 front-loaded with the purpose and then layers guards, cost, idempotency, and scope in six dense sentences. It is not bloated with restatement, but the guard sentence packs jargon without examples, so 4 rather than perfect.

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 write operation with annotations, a complete input schema, and an output schema, the description covers the essential caller-facing behavior: what it creates, prerequisites, cost, idempotency, refusal, and scope. No critical gap remains for correct 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?

Schema coverage is 100% and each parameter has its own schema description, so the schema already carries parameter semantics. The description adds only a typical sample length (30–120s) and retry reconciliation, which is useful but not a full substitute; baseline 3 is appropriate.

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 opens with a specific verb+resource: creates/selects an artist's own speaking voice from a confirmed sampleAssetId, and scopes the output to Film dialogue rather than song singing. It also gives a sample duration, which distinguishes this from catalogue-based voice selection, though it does not name sibling tools like studio_artist_voice_choose explicitly.

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?

Prerequisites are clear (owned confirmed sampleAssetId, typically 30–120s) and an exclusion is stated ('not song singing'), so the agent knows the context is Film dialogue. However, no explicit alternative tool is named for selecting an existing voice or handling missing samples, so the routing guidance stops short of the 5 level.

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