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

The annotations include destructiveHint=true, which signals mutation, and the description aligns with that. The description adds important behavioral context beyond the annotations: the value is sensitive, goes to a secret store, only the last four digits are recorded and returned, and the agent must not repeat or guess the value. This is valuable behavioral guidance that the annotations alone do not provide.

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 a single paragraph of moderate length. It front-loads the core purpose and then provides necessary handling instructions. Every sentence adds value: the sensitivity, the storage behavior, the return behavior, and the interaction rules. It is slightly dense but not bloated.

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 the tool's sensitivity and the presence of an output schema, the description covers the essential context: what the value is, how it is stored, what is returned, and how to handle it in conversation. It doesn't explicitly state prerequisites (e.g., that the owner must exist) or error conditions, but the output schema and the clear instructions make it sufficiently complete for an agent to invoke it correctly.

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 67%: ownerId and applicationId have descriptions ('UUID value wrapper'), but taxIdentifier has no description in the schema. The description explains that taxIdentifier is the SSN/ITIN and that only the last four digits are recorded, which adds meaning beyond the schema's bare pattern. However, it doesn't explicitly map the parameter names to the described behavior, and the two UUID parameters are only minimally described. The description partially compensates for the undocumented taxIdentifier parameter.

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 clearly states the action: setting the owner's tax identifier (SSN/ITIN) on a banking application. It specifies the resource (owner) and the field (tax identifier), and the context (banking application). It doesn't explicitly differentiate from sibling tools like formation_set_shareholder_tax_identifier or banking_set_owner_identity_document_number, but the verb 'set' plus the specific resource and field make the purpose clear enough.

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: it is needed for the owners section and cannot be completed without one for each assessed owner. It also gives explicit instructions on how to obtain the value: ask the person directly, pass it once, never guess it, never read it back, never repeat it. It doesn't explicitly name alternative tools or when not to use it, but the context is strong enough to guide an agent.

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