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

With annotations already declaring destructiveHint=true and readOnlyHint=false, the description adds the key context that 'replace' overwrites a prior verdict, that the opion is non-workflow-moving, and that users with viewer-level permission can call it. It stops short of describing the response or whether the previous comment is preserved, but it meaningfully extends the annotation surface.

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 tightly packed sentences: the action first, then the semantic caveat, then the permission note. Nothing is redundant and no sentence could be dropped without losing information.

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 4-parameter mutation with no output schema but full annotation coverage, the description conveys action, overwrite semantics, permission level, and side-effect boundary. The main gap is the response shape and the undocumented candidateId, which an agent must infer from the schema's UUID format 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 coverage is only 25% — only workspaceId is documented in the schema. The description covers verdict (superstar, yes, no) and the optional reason/comment, but candidateId is described nowhere, and the enum values are simply restated rather than enriched.

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 gives a specific verb and resource — 'Record or replace the signed-in user's verdict on a candidate' — and even enumerates the allowed verdicts. The 'signed-in user's verdict' scoping separates it from list_candidate_reviews and request_candidate_review, though no sibling is named 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?

'A verdict is an opinion and does not move the candidate between workflow steps' implicitly steers the agent away from using this instead of set_candidate_stage, and 'Viewers may review' signals the permission floor. However, no alternative tool is named, so the when-to-use-which decision is left partly to inference.

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