Start People Cleanup

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

The description claims 'read-only' while the annotations explicitly set readOnlyHint to false, a direct contradiction. It does add useful context with 'never automatically merges contacts,' but the contradiction undermines the agent's trust in the stated safety model.

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 compact and front-loaded: it states the core purpose in the first sentence, then adds the key safety guarantee and the sibling alternative. The cost and API-key note are useful operational details with little wasted text.

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 an output schema present, return-value explanation is unnecessary, but the description leaves major gaps: two core parameters are undocumented and unexplained, there is no guidance for choosing between this and several cleanup/audit siblings, and the read-only claim conflicts with the annotation.

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?

The schema documents only request_id and idempotency_key; checks and auto_merge_threshold have no description. The tool description adds no parameter semantics at all, and the unexplained auto_merge_threshold is especially confusing given the claim that the tool never auto-merges.

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 clear verb and resource: 'Server-side read-only cleanup audit. Returns a review queue.' It also distinguishes itself from normalize_people_preview/apply by explicitly saying it never auto-merges. However, it does not differentiate itself from similarly named sibling tools like cleanup_preview, audit_people, or get_people_cleanup_result.

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?

It gives one explicit routing instruction: use normalize_people_preview/apply for reversible normalization, implying this tool is for non-reversible audit/review. But it does not say when to prefer this over cleanup_preview, audit_people, or merge_people, nor does it give a when-not-to-use condition beyond normalization.

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