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

Goes well beyond the readOnly/openWorld/non-destructive annotations: it discloses source coverage and thresholds per country (TED "above the EU thresholds only"), that natural-person suppliers are never returned, and that company_id is only populated when the supplier resolves to a company record. It also flags data-quality traps an agent could otherwise misread — amount_is_ceiling is not spend, amount_suspect is a form default, amount_eur vs amount_contract_eur is a share vs whole-contract distinction.

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 and scope are front-loaded in the first clause, then the source coverage and one-row-per-award grain, then the field semantics. It is dense and long, but every clause carries decision-relevant information, especially since there is no output schema to explain the returned amount and competition fields.

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 an 11-parameter, no-output-schema, multi-country search tool, the description covers sources, thresholds, filtering defaults, result grain, amount semantics, competition signal and the mutual-exclusion precondition. An agent has everything needed to form a valid call and interpret the rows without further documentation.

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 100%, so the schema already documents every parameter, making 3 the baseline. The description adds only marginal parameter-level meaning beyond it — the country enumeration coverage across sources and the company_id-to-company_detail linkage, both of which are largely inferable from the schema text.

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 specific verb and resource ("List public-contract awards") plus filter dimensions and sort order ("newest first"), and adds a crucial grain statement ("One row per award to one supplier") that separates it from aggregate siblings like procurement_buyer or procurement_relationship. It never explicitly names a sibling or states what it is not, so it stops short of full sibling differentiation.

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 routing guidance for the country parameter ("pass country to restrict, omit it for all countries"), a hard precondition ("Requires at least one of company_id, nif, supplier, buyer, cpv or date_from"), and a follow-up pointer ("use company_detail on it"). It does not cover when to prefer procurement_buyer or procurement_relationship over this tool, so alternatives are only partly addressed.

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