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

Beyond the annotations (readOnlyHint, openWorldHint, idempotentHint, destructiveHint), the description discloses the critical window_complete flag semantics: a zero result does not mean 'not published', only 'absent from the notices examined'. It also explains that keyword matching is client-side because the FTS API has no text search and rejects a keyword parameter, which prevents an agent from assuming server-side search behavior.

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 long but dense; nearly every sentence carries operational guidance. The lead sentence front-loads the core purpose, followed by usage examples, then the critical window_complete caveat and the alternative tool. Some historical context about EU TED could be trimmed, but it helps explain the 'above-threshold' scope.

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 list/filter tool with no output schema, the description covers what an agent needs: corpus, ordering, keyword semantics, pagination caveat (window_complete), and when to choose an alternative. The keyless note and safety annotations remove ambiguity about authentication and side effects.

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 parameters are already documented. The description adds meaning by specifying that the keyword is matched over title, description, award title, and awarded supplier, which goes beyond the schema's 'filter recent notices by title/description'. The ordering guarantee 'newest-first' also clarifies what the limit parameter shapes.

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 explicitly states that the tool returns 'Recent HIGH-VALUE UK government tenders and contract awards from the Find a Tender Service', which is a clear verb-resource pair. It distinguishes itself from the sibling search_notices by positioning itself as the above-threshold Find a Tender feed rather than the full-corpus Contracts Finder search.

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 gives a rich set of 'Use for' query examples and explicitly names the alternative: 'For a proper full-corpus keyword SEARCH of UK procurement, and for lower-value notices, use search_notices (Contracts Finder)'. It also explains the practical implication of the client-side keyword filter and advises narrowing days when window_complete is false.

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