Correlation Path

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds meaningful behavior: it explicitly discloses the found:false return shape with the reason distinction (no edges vs different components) rather than an empty array, which is valuable behavioral context beyond annotations. Missing some context like hop semantics or path weighting, but no contradictions.

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 sentences, zero filler. The first sentence delivers the core value in one flowing clause, and the second sentence proactively handles the negative-return case. Every clause adds information.

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?

Output schema exists, so return values are documented separately. Both parameters are documented, annotations cover the safety profile, and the description handles the edge case (found:false) and the interpretation guidance (weakest-link strength, connectedness question). This is complete for a read-only graph-query tool.

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% with clear descriptions for to, from, and max_hops (including the 1-8 range and default 6). The description reinforces path semantics (hop count, weakest-link strength) that map to max_hops usage. It adds value by explaining what the path represents per hop, but relies largely on the schema which already documents all three parameters well.

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?

Clear verb-plus-resource ('Shortest evidence path between two threats across the similarity graph'), specific scope, and explicit answer to the analytical question ('is this incident connected to that campaign, and through what'). The output content is enumerated (intermediate threats, per-hop signal, weakest-link strength), which thoroughly distinguishes this from siblings like get_similar_threats or explain_correlation.

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 implies the tool answers connectivity questions between two threats but does not explicitly say when to prefer it over explain_correlation or get_correlation_subgraph, which appear as siblings and sound adjacent in purpose. No explicit when-not/alternative guidance, though the purpose statement ('Answers is this incident connected to that campaign') provides reasonable implied context.

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