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

Annotations already declare readOnly, idempotent and openWorld, so the safety profile is covered. The description adds genuinely new behavior: default sort order (soonest deadline first), page model via offset with total as full count, data provenance (same free facts as the llms-full.txt, detailed criteria live on officialGuidanceUrl), and a usage caveat to confirm deadlines/eligibility with the funder. It stops short of stating rate limits or failure modes, which is a minor gap rather than a serious one.

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?

Purpose, scope and sort order are front-loaded, and most sentences carry distinct information (closes_before hint, provenance, paging, date formats). The one waste is the duplicated sorting claim, stated once in the opening clause and again as 'Results are sorted soonest deadline first', plus a slightly long final stretch of format notes.

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?

With 8 all-optional params, no output schema and no nested objects, the description still tells an agent what a result contains, its ordering, how to page it, how the deadline fields differ, and how to answer closed-scheme questions. Nothing needed to call the tool correctly is missing.

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 meaningfully extends it: it clarifies the closes_before intent ('closing this month'), the offset/total paging contract, include_recently_closed's 90-day window, and the deadline vs deadlineUk format distinction (UK date when the source gave no time, otherwise an ISO instant) that the schema does not explain.

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 + resource + scope: search UK grant schemes that are open, rolling or forthcoming with a deadline not yet passed. The scope qualifier ('deadline not yet passed') and the enumeration of returned fields let an agent distinguish it from get_grant, count_matching_grants and the example/list siblings without opening a schema.

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?

Gives concrete when-to-use routing: 'Use closes_before for closing-this-month questions' and 'Set include_recently_closed ... to answer what was the deadline for X'. It also implies the search-vs-count split via 'total is the full count', but it never explicitly names count_matching_grants/get_grant as the alternatives, so the routing is clear rather than exhaustive.

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