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

With annotations present (readOnlyHint=false, destructiveHint=false, idempotentHint=true), the bar is lower, and the description still adds substantial context: quota consumption from a shared bundle, a mandatory consent step, an idempotency/retry contract for request_id, and a disclaimer that no human legal judgment is produced. These are operational traits the annotations do not express. It does not describe output shape, but that is minor 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?

Five short sentences, each carrying distinct operational information, with the blocking prerequisites (access, quota, consent) front-loaded before the analytical purpose. No filler or repetition. The trailing disclaimer sentence is slightly detached from the flow but still earns its place.

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 need not describe return values, and it does cover the non-obvious constraints (access, quota, consent, idempotency, non-human judgment). What it omits is the meaning of three required inputs and any sense of output form, which is a meaningful gap for a five-parameter tool with zero schema documentation.

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 0% across five parameters, so the description must carry the semantic load and it does not. It explains request_id's uniqueness/retry semantics and implies 'de aangeleverde tekst' maps to document, but rol, standpunt, and confirmed are never explained; confirmed can only be guessed at from the adjacent consent sentence.

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?

The description states a concrete purpose: it investigates counterarguments, evidentiary problems, and relevant sources for a supplied position. That is a specific analytical verb-resource, well beyond the vague name 'stress_test'. However, it never contrasts itself with plausible siblings such as check_source or make_memo, so an agent must infer the routing itself.

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 real invocation preconditions: document access is required, it consumes one question from the shared bundle, and consent must be obtained first. What it lacks is any explicit when-to-use-this-instead-of-a-sibling guidance or when-not-to-use condition, which matters given thirteen siblings with overlapping legal-research functions.

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