Zoek in de cao-kennisbank

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds valuable behavioral detail beyond that: results are labeled as 'geldt nu', 'historie', or 'open vraag' and include page and source link, telling the agent how to interpret result validity. No rate limits or auth requirements are mentioned, but those are not crucial here.

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?

Two tightly written sentences: the first front-loads purpose and return format, the second gives usage and examples. No filler, and the most important information (what is searched and what comes back) leads.

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?

With no output schema, the description must explain returns, and it does: matching text passages with labels, page, and source link. It does not elaborate on the meaning of the labels or result ranking, and the default result count is left to the schema. Adequate for a 3-parameter read-only search tool, with minor gaps.

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 baseline is 3. The description adds meaning for the main parameter by instructing to phrase the vraag in ordinary Dutch words and giving concrete examples. It also adds guidance for onderwerp ('Laat weg om overal te zoeken'), which goes beyond the schema's description of that field.

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 and resource: searches by keyword in the knowledge base about the Cao voor Uitzendkrachten and returns best-matching text passages. The return shape (text pieces with labels, page, source link) is specified, and it implicitly contrasts with siblings lees_onderwerp and onderwerpen by referencing the latter for page scoping. An agent can distinguish this keyword-search tool from the topic-listing and topic-reading 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?

Provides useful usage context: ask in plain Dutch, with examples like "wachtdagen bij ziekte", and the onderwerp parameter can restrict to one page or be omitted to search everywhere. However, it never explicitly says when to use this tool versus lees_onderwerp or onderwerpen, nor when not to use it. Usage is implied rather than routed.

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