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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered; the description adds genuinely non-derivable context: Blind Mode strips contact and personal data, each call costs one credit with a key, and keyless use is capped at 5 preview rows and 20 calls/day. Missing is anything about pagination depth limits or result ordering, but the added value is substantial.

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?

Four tight sentences with no filler; the source and Blind Mode constraint are front-loaded, and cost/rate limits come last where they belong. Slightly dense with parenthetical detail, but every clause carries information.

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 query tool with no output schema and no parameter documentation, the description covers provenance, privacy, boolean logic, and cost but says nothing about the returned fields, sort order, or how far pagination reaches. An agent could call it, but could not confidently construct a filtered query without guessing at parameter semantics.

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?

With 0% schema description coverage and 11 parameters, the description carries the full explanatory burden, yet it only clarifies one of them (q searches all text fields) and the AND-combination rule. Fields like cpv_codes, procurement_method, status, buyer, value_amount_min/max, and published_at_after/before are left to be inferred from their names alone, with no format or matching semantics (exact vs substring, code lists, inclusive bounds).

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?

Names a specific resource (public procurement notices) and a specific authoritative source (the official Find a Tender OCDS feed), plus the transformation applied (flattened to one queryable schema). That is enough to separate it from query_eu_ted and query_uk_contract_awards, though it never explicitly contrasts itself with those siblings.

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?

It gives real query semantics — filters combine with AND and q searches all text fields — plus cost and preview constraints that affect whether an agent should call it at all. But it never says when to prefer it over query_uk_contract_awards or query_eu_ted, and no exclusion or prerequisite guidance is offered.

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