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

Annotations establish only that this is a non-destructive write; the description adds the important behavioral facts: results are persisted, they are sanitized, the outcome is one of three enumerated verdicts, and retries are idempotent via operationId. Missing are permission requirements and whether repeated evaluation of the same version creates duplicate stored results.

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?

Two short sentences, front-loaded with the action and the outcome states, with no filler. The only weakness is that the retry/idempotency note is tacked on without connecting to which parameter it governs.

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?

With no output schema, the description usefully discloses the verdict vocabulary and that results are persisted. For a four-required-parameter mutation tool with zero schema documentation, though, an agent still lacks a description of the json input's expected shape and the meaning of workspaceToken versus policyId.

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% across five parameters, so the description carries the full burden and largely does not meet it. It clarifies operationId's retry role and implies version identifies an already-saved policy version, but workspaceToken, policyId and especially the "json" payload remain unexplained.

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?

"Evaluate one explicit saved policy version" states a specific verb, resource and scope, and the sentence names the three possible verdicts (ALLOW, WARN, BLOCK), which separates it from retrieval siblings like quality_policy_get or quality_policy_history. It stops short of explicitly naming those alternatives, so an agent must infer the distinction.

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?

The description gives one concrete operating rule — "Reuse operationId for an exact retry" — which is real guidance about when to repeat a call. It never says when to choose this tool over quality_policy_get, quality_policy_history or data_quality_check, so the selection logic is left implicit.

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