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

Annotations already declare this a safe, idempotent read, so the description correctly spends its words on non-obvious behavior: prefix-only matching, accent insensitivity, fallback behavior when no word matches (rows matching most words are returned and marked), and hard paging caps of 25 per page and 100 per query. It does not explain ordering beyond 'open calls first' or how the cap is surfaced to the caller.

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?

Information is front-loaded: what is searched, then matching rules, then filters, then results and paging. Sentences mostly earn their place, though the closing 'radar link' reference is compressed to the point of ambiguity for a first-time caller.

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 nine-parameter search with no output schema, the description covers result contents (public notice link plus radar link) and paging behavior, which is what an agent needs to invoke it correctly. Remaining gaps are minor: no explicit statement about result ordering beyond status, and the radar-link alternative is under-explained.

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 only 44%, but the description compensates for most of the gap: it explains query matching rules, status, country, kind of work, minimum value and firm filtering, and the paging limits that the schema only partially encode. The `lang` parameter's role (language of page links, data unchanged) is left to the schema, which does cover it.

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 (keyword search) over two named resources (open consulting calls, awards from the last six months) with geographic scope (Europe). The matching semantics (title, buyer, winners; prefix matching, accents ignored) further pin down exactly what is searched, so an agent knows what this tool does without opening the 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 concrete guidance on how to query (search in the notice's country language, or mix languages) and lists the available filters. It also points to an alternative path ('for a search by meaning, use the radar link'), though that alternative is a link inside results rather than a sibling tool, so routing is clear but slightly indirect.

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