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

Annotations only declare the operation profile (readOnlyHint false, non-idempotent, openWorld), which fits a tool that creates a batch. The description adds material context the annotations cannot carry: cost in units per row (+2 for name-only), free reuse of checks for 24 h, the asynchronous 'next' signal while still checking, and explicit scope boundaries ('a registry check, not KYB or sanctions clearance; no person's name').

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 and the exclusion, then organized under explicit Inputs / Returns / Limits labels. Dense but every sentence (cost, reuse window, scope disclaimer, async indicator) carries information an agent needs to call it correctly.

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?

No output schema exists, yet the description summarizes the return shape (counts by review_state, review rows with reasons, share_url, 'next'), and it covers cost, limits, exclusions and the batch_id read path. Nothing essential for correct invocation is missing.

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 the baseline is 3, and much of the row guidance is duplicated in the SupplierRow $def. It still adds selection semantics: the mutual alternative between rows and batch_id ('Leave out to read a batch_id'), and the conditional rule that a name alone only resolves with postal_code and street matching one company.

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 supplier list against the official registers') plus the output scope (ok / need a look and why, proof code, share link). It explicitly distinguishes itself from the sibling verify_company, so an agent can route correctly without opening either schema.

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 a concrete use range ('2 to 100 suppliers at once, or to read a batch you started') and an explicit exclusion with the alternative named ('Don't use it for one company: call verify_company'). When-to-use, when-not-to-use and the substitute tool are all present.

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