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

Annotations cover the safety profile (readOnly, idempotent, non-destructive, closed-world), but the description adds substantial behavioural context beyond that: it enumerates and interprets each relation type, discloses that overlap is a lead rather than a verdict and that possible-overlap is frequently wrong, and states which relations are excluded by default.

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 dense sentences, front-loaded with the purpose before the mode and relation semantics. The caveat sentences earn their place, though the closing tangent about overlap reliability and the trailing 'Canton-specific' are slightly loose.

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?

No output schema exists, yet the description explains what each returned group contains (relation type, confidence, the numbers behind it) and how paging/counting behaves, and all six parameters are documented in the schema. An agent has everything needed to call and interpret 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%, so the baseline is 3, but the description adds genuine meaning: it explains that `number` switches the whole output mode to neighbour listing, describes the Dev-Fund-Navigator default relation set versus the opt-in relations, and notes that min_similarity defaults are validated thresholds.

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 (find Canton Dev Fund proposals that duplicate, re-file or overlap) and names the comparison basis (meaning plus identical text, title, author, organization). It is clearly distinguishable from neighbours like detect_builder_overlap, find_similar_projects and get_proposal.

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 spells out the two modes: without a number it lists groups, with a number it lists the closest proposals to that one with evidence. It also states the default filtering (only groups with an open proposal) and when the softer relations like amendments and same-applicant relations are returned (only when asked for).

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