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

The description provides extensive behavioral transparency: it uses deterministic rules (no LLM on verdicts), excludes ineligible grants, costs $0.15 USDC per call, and returns a specific result shape. No annotations exist, so the description carries the full burden and delivers rich, critical details about behavior, costs, and ethics (ineligible grants never dressed up as options).

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?

The description is front-loaded with the main purpose and provides a clear, detailed overview in two substantive paragraphs. Every sentence adds value (cost, determinism, result structure). It is slightly longer than necessary but still efficient. A very minor deduction for density—could be split into briefer chunks, but overall it is well-structured.

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?

Given the tool's moderate complexity (nested input, no output schema), the description is comprehensive. It specifies cost, deterministic behavior, and the exact output format (matches with eligibility table, excluded counts). Despite no output schema, the description fully explains return values. The richness compensates for the lack of annotations and partially weak schema coverage.

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 50%, with 'top' well-defined by schema (type, default, min/max) and 'project' described but with nested properties lacking descriptions (e.g., 'keywords' and 'description' only have empty descriptions). The description adds value by explaining the overall usage (send project profile with 'what it is, who you are, where, how much you need'), which helps agents understand how to populate the nested object. The description partially compensates for the schema gap, but detailed parameter semantics for nested fields remain thin.

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 description clearly states the tool's purpose: matching a project profile to eligible UK grants and returning ranked results. It distinguishes itself from siblings like 'uk_grants_search' by emphasizing eligibility-based matching with a per-criterion pass/fail table, not just a search. The verb 'Match' and resource 'project profile to eligible UK grants' are specific and unambiguous.

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 explicitly explains when to use this tool: when you need to find grants a project could actually get. It contrasts with 'uk_grants_search' implicitly by stating it returns ranked eligible-first matches with pass/fail details. However, it does not explicitly say when NOT to use it (e.g., if only a simple search is needed) or name alternative sibling tools for specific use cases. The guidance is clear but lacks exclusions.

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