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

Beyond readOnlyHint and openWorldHint, the description discloses what each result carries (section-level source, retrieval time, version date, what was not checked), the five-way outcome summary (resolved, name-only, ambiguous, not found, unknown), and unavailable sources. It also states two non-obvious behavioral rules an agent could not infer: ambiguous names are never resolved by guess, and billing is waived when nothing can be checked.

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 scoping and identifier options are front-loaded, and the trailing clauses on ambiguity handling, billing and non-compliance each earn their place. It is a single heavy sentence-chain though, and the output/summary detail is packed in at the cost of easy scanning.

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?

For a paid, batch, read-only lookup with an output schema, the description covers inputs, per-result structure, summary categories, ambiguity policy and billing behavior. An agent has enough to decide between this and entity_evidence_check and to call it correctly in one pass.

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 nested company fields, maxItems 10, minItems 1 and 'order kept' are already documented in structured data. The description adds only marginal meaning by restating the identifier types accepted and the allowed range, hitting the baseline rather than extending it.

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 opens with a precise verb and resource plus an explicit anchor to the sibling: the same check as entity_evidence_check, but batched over 1-10 Japanese organizations, with the accepted identifier types (corporate number, exact name, registration number) named. An agent can distinguish this batch tool from the single-record sibling 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?

The '1-10 ... in one call' framing makes the batch selection condition clear relative to entity_evidence_check, and 'Not charged if no company can be checked' plus 'Not a compliance determination' set real boundaries on use. It stops short of stating an explicit when-not-to-use or naming the single-company tool as the alternative for one record, so 4 rather than 5.

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