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

Annotations already cover readOnly, idempotent and openWorld=false, so safety is not the loader. The description adds real behavioral value beyond them: the response fields (bronlink, letterlijk bronfragment, ingangsdatum, datakwaliteit) and an explicit anti-hallucination constraint ('Geef nooit bedragen die niet in het antwoord staan'), which is important for an authoritative-amounts tool.

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 purpose, then the module enumeration, then the search-fallback rule and the accuracy guard. The module list is long but each item is field-relevant, and every sentence earns its place with no filler.

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 correctly compensates by naming the returned fields. An agent has enough to call the tool and interpret results; the only missing piece is cross-tool routing versus the CAO/CBS siblings.

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 baseline is 3, but the description goes further by naming the valid module values (minimumloon, inkomstenbelasting, toeslagen, etc.) in a schema that has zero enums, and by explaining the intended use of 'zoek' versus 'key'. That materially reduces the risk of an invalid module string.

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 + resource ('Geeft officiële Nederlandse financiële bedragen') plus the returned metadata and an enumerated module list, so the agent knows exactly what domain this covers. However, it never distinguishes itself from the sibling tools (cao_zoeken, cbs_loontrends, cao_details), which an agent must disambiguate on its own.

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?

It gives one concrete routing rule — use 'zoek' when the exact key is unknown — which is genuinely useful parameter-selection guidance. But it provides no when-to-use / when-not-to-use guidance relative to the sibling CAO and CBS tools, leaving tool selection to inference.

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