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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=true, openWorldHint=true), and the description adds genuinely new behavior beyond them: EU VAT ids are validated against VIES, the specific failure code billing.vat_check_unavailable is retryable by resubmission, and success returns 202 with an operation to poll. These async/external-validation/retry semantics are exactly the kind of context annotations cannot convey.

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?

Three sentences, front-loaded with the what, then the when, then behavior; no filler. Slightly dense in the VIES/retry clause and mildly overlaps the schema body note about VAT-vs-country checking, but each sentence 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?

An output schema exists so return values needn't be explained, yet the description still notes the 202 + poll pattern. Combined with the safety annotations and the field enumeration, an agent has enough to invoke it, with the only real shortfall being the undocumented legal_entity_type/tenant_id details.

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 only 33%, so the description must compensate, and it does list the main body fields (legal-entity name and type, VAT id, invoice address, invoice email, optional PO reference) and flags PO reference as optional. However, it omits format-level detail such as the legal_entity_type pattern, the tenant_id parameter, and the address sub-fields by name, leaving meaningful gaps.

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 ('Complete the tenant's billing details') and enumerates the data involved (legal-entity name/type, VAT id, invoice address, invoice email, PO reference). An agent can tell what the tool does at a glance, though it never explicitly contrasts itself with the read-only sibling get_billing.

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 clear triggering condition: 'Call this when the owner or a billing contact has the details.' That is real context, but it offers no explicit when-not guidance or named alternatives (e.g., get_billing to read, get_legal_entity_types to look up the legal-entity code).

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