list_duplicate_candidates

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

The annotation set declares readOnlyHint=false, and the description explains exactly why: 'Reads only (may create the project database)'. That is genuine added context beyond the structured hints, and the idempotent/no-destruction profile is consistent. It does not discuss pagination or what 'pending' means semantically, keeping it below 5.

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 clauses: purpose/scope first, routing second, with the side-effect caveat parenthetically folded in. No filler sentences and nothing repeated from the schema.

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 scope, the handoff sibling, and the surprising write side effect. What is missing is only minor orientation (e.g., that results are pending items awaiting a decision), which is implied rather than stated.

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 100%, so the schema already documents limit, run_id, and project thoroughly. The description adds no syntax or semantics for the parameters themselves (no mention of the limit cap or run_id scoping), so baseline 3 applies.

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 ('List pending entity pairs that may be the same thing') plus the returned detail ('an example mention of each'), and names the sibling that consumes the output (resolve_duplicates). An agent can immediately distinguish it from resolve_duplicates/merge_entities.

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?

Explicitly routes the agent to resolve_duplicates for the decision step, so the when-to-use-next is clear. It does not state when not to call it (e.g., after all duplicates are resolved) or any prerequisite ordering beyond the run_id/project params, so it falls short of a full 5.

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