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

Goes well beyond the annotations: it discloses that the full number is routed to a secret store while only the last four digits are persisted and returned, that a kind mismatch is refused, and that the value must be passed exactly once and never echoed back. These are non-obvious security and validation behaviors an agent cannot infer from destructiveHint/openWorldHint.

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?

Four sentences, front-loaded with purpose before guidance, and each sentence carries operative information. It is slightly dense with stacked imperatives ('never guess it, never read it back...'), but nothing is wasted.

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 mutating tool with annotations, a nested-object schema and an output schema, the description covers what matters: the prerequisite for completion, the SSN/ITIN classification rule, and the secret-handling contract. Nothing an agent needs to call it correctly 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?

With schema coverage at 50%, the description compensates usefully by explaining the kind parameter's semantics that the bare enum labels do not convey (ITIN starts with 9, SSN never does, mismatch refused). It adds little for ownerId/applicationId, but those are self-describing UUID wrappers in the schema.

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 — filing one beneficial owner's SSN/ITIN against a banking application — with clear scope ('one', 'beneficial owner'). This is readily distinguishable from siblings like banking_set_application_ein (company EIN) and banking_set_owner_identity_document_number (a different document type).

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 concrete operating instructions: ask the person which of SSN/ITIN they hold, pass it as kind, and the prerequisite that each assessed owner needs one for completion. It does not, however, name a sibling alternative for cases where the identifier lives elsewhere (e.g. formation_set_shareholder_tax_identifier).

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