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

Annotations already declare readOnly, idempotent and closed-world, so the safety bar is low; the description then adds real behavioral context beyond them — API key requirement, plan-dependent batch size and history window (Trial: 5 customers, 24 months), and the fuzzy-match/ZIP-gating rule. It stops short of describing failure modes or how partial/ambiguous results are ordered across a batch.

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-loads the core operation and the return shape, then tucks the ZIP caveat and plan limits at the end. It is dense but every clause is informative; the return-field enumeration is slightly cluttered but still readable in a single pass.

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 present, the description carries the return-value burden and does so — status, matching companies best-first, confidence, match_basis, stage, and the `ambiguous` flag. Auth and quota constraints are also covered, leaving only error/partial-failure behavior unaddressed for a moderately complex batch tool.

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 only 33%, and the description meaningfully compensates for the zip field by explaining that a name match only counts when the ZIP appears in the notice. However, `since` and `min_confidence` — including the 0.85 default that governs what counts as a match — get no explanation in the description, and neither does the `ambiguous` output interaction with confidence.

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 ('check a list of business partners') plus the matching mechanism ('same fuzzy matching as the Insolvenzmonitor monitoring'), which tells the agent this is a batch lookup rather than a single-entity lookup. It never names check_company as the single-record alternative, so sibling differentiation is only implied by the word 'list'.

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 conditional guidance for one parameter ('Send the 5-digit ZIP if known — with a ZIP, a name match only counts if the ZIP appears in the notice') and states plan-based limits. But it never says when to prefer this over check_company for a single customer, nor what happens when the batch exceeds the plan limit, so tool-selection guidance stays implicit.

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