suggest_duplicate_threads

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so 'No writes' is largely redundant. The description does add genuine interpretation context — conservative same-goal matching and that forge-backed work stays separate — which helps the agent reason about output, though it omits anything about result ordering or confidence signals.

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?

It is short and front-loads the action, but sentences are fragmentary and idiom-heavy, and 'No writes' duplicates the annotation rather than earning its place. The middle two sentences read as policy notes whose practical meaning is unclear without domain knowledge.

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 not be explained, and the annotations carry the safety profile. What remains missing is the call-selection context: when this beat check_overlap or feeds into request_thread_merge, and what 'forge-backed' means for a caller deciding to invoke it.

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 100% and both parameters are documented in the schema, including the 1–50 range and the thread_id semantics, so baseline 3 applies. The description adds no parameter-specific detail beyond that, and does not explain how 'limit' interacts with confidence ranking.

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 verb+resource ('Review overlap suggestions') is identifiable, but the object is obscured by unexplained jargon: 'finishable outcome,' 'same-goal evidence,' and 'forge-backed.' An agent can guess this surfaces possible duplicate threads, but nothing in the text explicitly says so and no sibling (e.g., check_overlap) is named as the alternative.

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?

There is no explicit when-to-use framing and no routing against siblings like check_overlap, request_thread_merge, or thread_merge_history. The only guidance is interpretive ('related work is not a merge candidate'), which tells the agent how to read results rather than which tool to call.

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