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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds meaningful non-obvious behavior: it recomputes selection, discloses the deduplication rule ('Edition duplicates cannot inflate independent support'), and clarifies the output's semantic boundary. It stops short of describing the actual return shape despite having output schema, which is fine.

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?

Three tightly packed sentences, front-loaded with the core action, then the deduplication rule, then the scope caveat. No filler; every clause adds value.

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?

For a read-only analysis tool with an output schema, the description covers purpose, key heuristic behavior, and scope boundaries well. The only omission is parameter guidance for source_ids, but the output schema reduces the need to explain return values, so the definition is largely 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 description coverage is 0% – neither 'question' nor 'source_ids' has a description in the schema. The description mentions the concept of a question but provides no guidance on source_ids (optional array, max 4, specific ID pattern) or its role in scoping the selection. With the schema silent and the description not compensating, parameter meaning is a real 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 precise verb+resource ('Recompute evidence selection... and explain... heuristic coverage') and names the specific output categories (Strong, Limited, Insufficient). The closing clause 'This explains selection, not factual correctness' decisively distinguishes it from siblings like find_evidence_gaps and retrieve_evidence.

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 phrase 'This explains selection, not factual correctness' sets a clear scope boundary about what the tool is for and implies what it is not. However, it does not name specific sibling alternatives (retrieve_evidence, find_evidence_gaps) or state when to choose this over them, leaving some routing inference to the agent.

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