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

Annotations only declare read-only, idempotent, open-world and non-destructive traits. The description goes well beyond them: it discloses the $0.03/call x402 USDC-on-Base pricing, that data is fetched live on every call (no caching), that there is no charge on empty results or source failure, and the 25-notice cap with next_cursor pagination.

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-loaded pricing, then scope, then explicit use/don't-use blocks — well structured and dense. Minor waste: the $0.03 price is stated twice (opening line and closing line), and the sample pitch repeats the free-call idea already implied by 'No charge when nothing matches.'

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?

No output schema exists, and the description compensates by enumerating the returned fields (title, buyer, published/deadline, value/currency, CPV codes, procedure, notice URL, next_cursor). Billing, limits, pagination and failure behavior are all covered, so an agent needs nothing else to call it correctly.

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 baseline is 3. The description adds value beyond the schema by restating the fts default, tying limit to the 'up to 25 newest' behavior, and explaining that next_cursor comes from a prior response, and linking sample:true to the no-charge path — though most of this also lives in the schema.

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 and resource: fetch up to 25 newest UK tender notices from two named sources (Find a Tender or Contracts Finder), read live per call. The UK scope and named feeds distinguish it from au-contracts, fr-tenders and the generic tenders sibling without needing either schema opened.

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?

Explicit 'Use when' (fresh bid opportunities, buyer tracking, CPV codes and deadlines) and 'Don't use when' (contact people, award winners, full documents, non-UK notices) blocks, plus a pointer to sample:true for a free trial call. Nothing is left to inference.

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