resolve_duplicates

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

Annotations already flag destructiveHint=true and non-idempotent, and the description reinforces this by disclosing 'merge (irreversible; keep picks the survivor)' and that 'distinct' means the pair is not suggested again. That is real consequence-level context, though it omits batch-size limits and partial-failure behavior.

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 tight sentences with the action, consequences, and rules pointer front-loaded; every clause earns its place and nothing is redundant.

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?

An output schema exists, so return values need no explanation, and the description covers actions, irreversibility, pair source, and rule lookup. The gap is parameter-level detail for the decision objects and batching limits, but for a well-annotated mutation tool this is close to complete.

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%: `project` is documented in the schema, but `decisions` and its fields rely on titles/enums. The description adds meaning to `keep` ('keep picks the survivor'), yet says nothing about `reason`, `entity_id`, or `candidate_id`, so it only partially compensates for the coverage gap.

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+resource ('decide pairs') and names the exact upstream source (list_duplicate_candidates) plus the two outcomes (merge/distinct). An agent can distinguish this from siblings like merge_entities and list_duplicate_candidates without opening the schema.

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?

Clear context: decisions operate on pairs from list_duplicate_candidates, and it points to guide("duplicates") for the governing rules. It does not, however, state when to prefer this over merge_entities or any preconditions/ordering beyond the implicit candidate flow.

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