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

Annotations already mark this as read-only, idempotent, and non-destructive. The description adds valuable behavioral context beyond those: the check is offline, format-only, not proof of registration, costs $0.002 per call, supports a prepaid header or free daily call, and requires no wallet/API key. This gives an agent cost, authentication, and expectation-setting details that annotations do not cover.

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 description is compact and front-loaded: the core purpose and scheme list appear first, followed by the format caveat and cost/auth details. It is telegraphic but each clause adds useful information for selection or invocation. The pricing block is slightly tangential to tool behavior but still relevant for an agent deciding cost.

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?

Given only two required parameters, a rich annotation set, and an output schema, the description covers the main operational essentials: supported formats, offline behavior, checksum capabilities, required inputs, cost, and auth requirements. The main gap is the absence of exact kind enum values, which keeps this from being fully complete.

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 100%, so the baseline is 3. The description adds that 'kind= selects the scheme' and that kind/value are required, but it does not enumerate the exact accepted kind strings, even though it lists human-readable scheme names. An agent may still be unsure whether to send 'EIN', 'US_EIN', or 'ein'.

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 specific verb ('format first' / check) and a precise resource: offline tax/customs ID format validation for EORI, EIN/SSN, NINO, ABN, VKN/TCKN, and CA BN. It clearly differentiates itself from likely siblings like vat_check by scoping to these schemes and emphasizing format-only validation.

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 description gives clear context for when the tool is appropriate: validating tax/customs ID formats offline. It also warns that a well-formed ID is not proof of registration, which is an important usage boundary. It does not explicitly name alternative tools such as vat_check or company_lei, but the supported scheme list makes the intended use reasonably clear.

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