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

Annotations declare readOnlyHint=false and destructiveHint=false; the description is consistent with that, spelling out that it never changes, merges, or deletes contacts and that there is nothing to undo. It also adds cost ($0.15), the API key requirement, and the 30-day reversibility window of the follow-up apply tools — meaningful 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?

Front-loads the core behavior ('server-side cleanup audit... returns a review queue') and then packs the non-destructiveness, the follow-up pipeline, cost, and auth into a compact block. No filler sentences, though the final parenthetical mixes two unrelated facts (price and auth).

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 values need no explanation, and the description covers safety, cost, auth, and downstream workflow. The gap is the undocumented checks and auto_merge_threshold parameters, which leaves this otherwise complete definition with one blind spot.

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 50%: request_id and idempotency_key are documented in the schema, but checks and auto_merge_threshold have no schema description and are not mentioned in the description either. auto_merge_threshold in particular sounds consequential and sits awkwardly beside the claim of never merging contacts, and the description does nothing to clarify it.

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?

States a specific verb and resource: a server-side cleanup audit that records a run and returns a review queue. It names the downstream apply tools, so an agent can see its place in the pipeline, but it never distinguishes itself from close siblings like audit_people, cleanup_preview, or score_people_duplicates.

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 the post-cleanup workflow (merge_people_preview → merge_people, normalize_people_preview → normalize_people_apply), which is genuinely useful routing. However, it never says when to start this tool versus audit_people, cleanup_preview, or find_identity_candidates, so selection guidance is only implied.

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