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

Beyond the readOnly/idempotent annotations, it discloses meaningful behavior: questions are ordered, each carries allowed values and its mapped Scenario field, and the tool deliberately 'provides information, not advice' with the user signing up with the insurer themselves. That is a substantive scope/liability constraint an agent could not infer from annotations, though nothing is said about the size or format of the returned list.

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 response shape is front-loaded in the first clause and the operating rules follow in short imperatives. The long mid-sentence enumeration of intake topics is dense but each item is load-bearing for planning the conversation, so little could be cut without loss.

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?

An output schema exists, so return values need no explanation, and the safety profile is fully covered by annotations. The description supplies the domain fields, ordering rule and the advice disclaimer, leaving only minor gaps such as whether the questions are re-requestable or stateful across calls.

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 single parameter 'taal' has 100% schema description coverage with its enum and default documented, so the schema already does the work. The description never references language at all, adding no meaning beyond the structured field, making baseline 3 correct.

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 ('Returns the ordered intake questionnaire') and ties it explicitly to its downstream consumer, 'building a Scenario for bereken_jaarkosten'. The enumeration of what the questionnaire covers (insurance year, persons, deductible, collectiviteit, payment term) makes it unmistakable against siblings like bereken_jaarkosten or get_polis.

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 operating guidance: 'Ask only what is needed, in this order', and restricts planned care questions to cases where 'the user offers it', explicitly excluding diagnoses. It implies the follow-up (berecken_jaarkosten scenario building) rather than naming when not to use this tool, so it stops just short of full when/when-not coverage.

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