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

Annotations already cover safety (readOnly, idempotent, non-destructive), and the description adds material context beyond them: the two-week rolling window with daily refresh, one-row-per-award-and-supplier flattening, organisation-level granularity, AND-combination of filters, and credit cost with an unauthenticated preview cap of 5 rows / 20 calls per day. That is unusually rich behavioral disclosure for a read-only tool.

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?

Front-loads the value proposition, then layers scope, filter semantics, and cost in a logical order. The dash-delimited field list is dense but efficient; no sentence is filler, though the single sentence enumerating eight fields is long enough to be slightly heavy.

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 no output schema, the description usefully enumerates the returned fields (buyer, supplier, company number, award value and date, contract period, CPV codes, category, procurement method). It omits the response envelope and pagination behavior for a 15-parameter, paged tool, which is the notable remaining gap.

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 description coverage is 0%, so the description must carry parameter meaning, and it only partially does: it explains that filters combine with AND and that q searches all text fields. The other parameters (award_value_amount_min/max, award_date_after/before, published_at_*, cpv_codes, supplier_company_number, page/per_page) are left to self-explanatory names with no format guidance, which matters for the date and code fields.

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?

Opens with a precise verb+resource framing ('Who won which UK public-sector contract, for how much') and names the data source and row grain (Contracts Finder OCDS, one row per award and supplier). It distinguishes itself conceptually from query_uk_tenders by focusing on award notices, but never names that sibling, so the boundary between 'awards' and 'tenders' is left for the agent to infer.

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 usage constraints: a rolling two-week window refreshed daily, organisation-level data only, AND-combining filters, and q as a full-text search. It does not explicitly state when to prefer this over query_uk_tenders or query_eu_ted, which is the main gap given how easily awards could be confused with tender opportunities.

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