Onderwerpen van 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 the safety profile is covered. The description adds value beyond that by disclosing what each entry returns (name, coverage, applicable period, last-updated timestamp), which is meaningful given there is no output schema, but it says nothing about result size or how listing interacts with the 'per pagina' framing given there are no pagination parameters.

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?

A single dense but front-loaded sentence: the action leads, the returned fields follow, and the usage condition closes it. No filler or redundant restatement of the title.

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 zero-parameter, read-only listing with no output schema, the description covers what the tool does, what each entry contains, and when to reach for it. The only soft spot is the slightly ambiguous 'per pagina' phrasing (implies pagination that the empty schema does not expose), which an agent may briefly puzzle over.

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?

The tool takes no parameters, so per the rubric the baseline is 4. Nothing in the description needs to compensate for undocumented inputs.

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 ('Geeft de lijst met onderwerpen in de kennisbank') scoped to the Cao voor Uitzendkrachten, and contrasts with searching by noting it is the fallback 'als zoeken niets oplevert'. It is clearly distinct from lees_onderwerp (single topic) and zoek (search), though it never names those siblings explicitly.

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 two explicit trigger conditions: browsing what the knowledge base contains, or recovering when a search returns nothing. That effectively communicates the alternative to zoek, but gives no negative guidance (e.g. when lees_onderwerp is the better call once you already know the topic name).

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