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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds genuinely new traits: the call is free, the state survives restarts, and 'Pending is not saved' warns against misreading an in-flight result as success. It doesn't say how long state is retained or what happens to expired request ids.

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-loaded with the core read operation and the identifiers, followed by short operational notes. Sentences are terse to the point of fragments ('Free.'), but none are wasted and the ordering (what → when → caution) is sound.

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 status tool with no output schema, the description never enumerates the states that can come back (pending/done/failed) or what to do on each beyond 'pending is not saved'. It's adequate to call correctly but leaves the agent guessing at the response shape.

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 0% (only UUID patterns), so the description must carry the meaning, and it does: saveRequestId is clarified as the save's clientRequestId and designRequestId must be the original one. That disambiguation is the single most valuable thing to say here; retention/format details are still absent.

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?

Specific verb ('Read the state') plus the exact resource ('an earlier soclo_hosted_voices_save') and the two identifiers that address it. It is immediately distinguishable from sibling soclo_hosted_voices_save, which creates the save this tool inspects.

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 concrete triggering conditions: after a lost reply or restart, and after an uncertain result. The closing line ('Never invent a new request after an uncertain result') implicitly steers the agent away from re-calling the save tool, though no sibling is named explicitly as an alternative.

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