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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description layers on real behavioral context: daily-refreshed two-week window, organisation-level-only granularity, one row per award/supplier, 1 credit per call, and a 5-row preview capped at 20 calls/day without a key. That is value well beyond the structured fields.

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?

A single dense paragraph that front-loads what the resource is, then the data scope, then filter semantics, then cost. Every sentence carries information, though the long en-dash field list makes it denser than ideal.

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 15-parameter, no-output-schema read tool, the description covers what is returned, the window, granularity, filter combination semantics, and cost/preview limits. The main remaining gap is pagination behavior for page/per_page, which an agent must infer.

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% across 15 parameters, so the description carries the burden and largely does: it enumerates the queryable/returned dimensions (buyer, supplier, company number, award value and date, contract period, CPV codes, category, procurement method) and explains that q spans all text fields and filters AND together. It leaves date-format and page/per_page interaction unexplained, so not a full 5.

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: award notices from the Contracts Finder OCDS feed flattened to one row per award and supplier. It also implicitly distinguishes itself from the sibling query_uk_tenders by framing the resource as awards ('who won which contract, for how much') rather than tenders.

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 operating context: a rolling two-week window refreshed daily, filters combining with AND, q searching all text fields, and credit/preview cost limits. It stops short of explicitly naming when to prefer a sibling such as query_uk_tenders, so it is clear but not fully routing.

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