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

Annotations cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower, and the description still adds real context: sign-in is required via connect/connect_verify first, the result is a heading index rather than annotated metadata, and result_count=0 is not proof of no match. It stops short of describing pagination or the exact shape of returned rows.

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?

The description is a single dense paragraph ending in an enormous run-on enumeration of article numbers across gdpr, eu-ai-act, cra, nis2 and dora that is very hard for an agent to parse and largely redundant with the step-by-step guidance that precedes it. The important routing rules are buried mid-paragraph instead of being front-loaded.

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?

There is no output schema, so the description carries the return-value burden and does name the relevant fields (result_count, also_named, heading_note), plus the auth prerequisite and a fallback path when nothing matches. It is operationally complete for a 6-parameter lookup, with only row-level shape left implicit.

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 the baseline is 3, but the description goes further by enumerating accepted role words per regulation (deployer, provider, importer, controller, supervisory authority, notified body on eu-ai-act, etc.) and by clarifying the search-style query alias that agents pass by mistake. system_class is described as an optional class in the same title with the 'high-risk' example.

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?

The second sentence states a specific verb+resource: it returns articles whose official title names a role as an obligation addressee, backed by a concrete example (role='deployer', optional system_class='high-risk'). It is distinguishable from siblings like search_regulation and read_unit, which are named as complements rather than substitutes. The opening auth sentence dilutes the front-loading but does not obscure the purpose.

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 when-to-use rules: read also_named when result_count is 0, fall back to heading_note plus search_regulation when also_named is empty, then read_unit each article because the index is not a complete duty set. It also names alternatives (search_regulation) with the exact condition that selects them, and gives a prerequisite path (connect/connect_verify).

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