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

Annotations already declare the mutation/idempotency/safety profile, and the description adds real context on top: no cost, the need for a stable clientRequestId, and a recovery path. It does not say what the save returns (e.g., a saved voice ID) or how name collisions are handled, which is the main remaining gap.

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, front-loaded with what the tool does, then the durability rule, then the recovery rule — nothing wasted. The final clause ('after reconciling a missing admission, resending the exact saved request') is dense jargon that needs the schema description to fully parse.

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 mutating, idempotent, open-world tool with no output schema, the risky behaviors (cost, idempotency, recovery) are covered. What an agent still lacks is the result shape and any preconditions on name/previewId validity beyond the schema patterns.

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 20%, and the description compensates for just two of five parameters — clientRequestId (must be stable across retries) and retryAdmission. previewId, designRequestId, and name are only constrained by regex/length in the schema, with no semantic explanation of where they come from.

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 — 'keep a chosen preview as a saved voice' — and adds the cost trait ('free'). It names the sibling it interacts with (soclo_hosted_voices_save_status), so an agent can separate the save action from the preview/design/status tools in the hosted_voices family.

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 explicit sequencing (must already have a chosen preview), an explicit alternative on uncertainty ('read soclo_hosted_voices_save_status with the original IDs ... rather than inventing a new request'), and a hard precondition for retryAdmission ('only after reconciling a missing admission'). The when-not conditions are as clear as the when conditions.

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