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

The annotations already declare idempotency and non-destructiveness, and the description adds useful scope boundaries: it is not publishing or improving, new runs remain separate, and there is no provider work. It does not cover permission requirements or what happens on version conflicts, but it adds meaningful behavioral context beyond the annotations.

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 short, front-loaded, and each sentence adds a distinct constraint: scope, required version/idempotency inputs, run isolation, and absence of provider work. The only weakness is that 'saved stateVersion' introduces ambiguity rather than precision.

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 mutation tool with four parameters, no output schema, and 0% schema description coverage, the description leaves important gaps. Workspace is undocumented, version-conflict behavior is unexplained, and runId is only implied, so an agent cannot fully understand parameter semantics from the description alone.

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%, so the description must carry the load. It mentions 'saved stateVersion and idempotencyKey,' which loosely maps to expectedVersion and idempotencyKey, but the term 'stateVersion' does not match the schema's 'expectedVersion,' the optional workspace parameter is entirely unmentioned, and runId is only obliquely implied.

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 states a specific verb and resource: 'Mark one recorded answer run reviewed.' It also scopes the action by saying 'not published or improved,' which helps distinguish it from write-oriented siblings, but it does not explicitly name any alternative tool.

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?

Usage is implied by 'Mark ... reviewed, not published or improved' and 'New runs remain separate,' suggesting this is the narrow review-only action. However, it never explicitly says when to use this versus siblings like read_latest_answer_reviews, restore_answer_evidence, or review_preparation_action.

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