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 real behavioral context beyond them — the quality_caveat field emitted on unanchored searches, the relevance-only ranking in that mode, the latency difference, and how prefer_consolidated changes which text variant is returned. It does not discuss limit/pagination behavior, so not a full 5.

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 with corpus scope, then usage, then filters, in one dense paragraph with no filler sentences; every clause carries content. It is long and repeats the celex imperative already stated in the schema, which keeps it short of a 5.

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 10-parameter search tool with an output schema present, the description covers what the agent still needs: corpus boundary, anchor-vs-unanchored behavior, the degraded-result signal, and the narrowing filters. Return-value details are legitimately left to the output schema.

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 80% (baseline 3), and the description adds prioritization the schema cannot: celex as the mandatory 'anchor' equivalent to naming an issuer, article as a know-it-when-you-see-it filter, and the issuer-vs-cross_company default relationship. It reinforces rather than merely repeats the schema, though the raw field definitions for limit and profile remain the sole source.

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 (Search) and a precisely bounded resource (the text of EU financial regulation across a named 29-act corpus), enumerating the covered domains and the returned unit types (Article-paragraphs, recitals, annex blocks with breadcrumbs). It also explicitly carves out scope ('not all EU law'), so an agent can separate it from the sibling filing/partner/transcript search tools without opening any schema.

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 explicit routing rules: ALWAYS pass `celex`, add `article` when known, and use `scope=cross_company` deliberately for genuinely corpus-wide questions, with a concrete example ('which acts impose a 72-hour incident-reporting deadline'). It also names the consequence of the wrong path (no celex -> whole-corpus, relevance-only, quality_caveat), which is exactly the when/when-not guidance an agent needs.

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