Update Person Identity

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

Annotations only say readOnlyHint=false and destructiveHint=false, leaving room for the description to add value. The description discloses that confirmed user_relationships are preserved unless force=true, which is a critical non-obvious behavior. It also adds the policy constraint 'Never infer sensitive identity from appearance' and notes the $0.10 cost plus API key requirement. These go well beyond the structured annotations.

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 two sentences long, with the core purpose and field list front-loaded. The additional behavioral and cost/auth notes are appended at the end without redundancy. Every sentence earns its place, and there is zero filler.

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 complexity (11 parameters, nested objects, an output schema), the description covers the key behavioral nuance about preserving user_relationships and the cost/auth requirements. However, it does not explain the shape of nested objects or provide any guidance on how to construct values for aliases, social_handles, or user_relationships. It also does not explicitly set expectations about the output, though an output schema exists. While not wholly inadequate, it leaves gaps for an agent that needs to build valid payloads.

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 18% (only request_id and idempotency_key have descriptions). The description lists the field groups (legal/preferred name, pronouns, social handles, user_relationships) but does not explain the structure of nested objects like aliases, social_handles, or user_relationships beyond their names. It does clarify the semantics of the force parameter within the preserve/force=true note, which partially compensates, but with 11 parameters and heavy nesting, the description should provide more detail.

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 'Patch identity fields' and then enumerates exactly what those fields are: legal/preferred name, pronouns, social handles, user_relationships[]. This is a specific verb+resource pairing that immediately distinguishes it from sibling tools like update_person or update_person_alias. The mention of 'identity fields' makes the scope unambiguous.

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?

Usage is implied by the 'identity fields' phrasing, which suggests it is for identity-related updates rather than general person edits, but no explicit guidance is given about when to prefer this tool over update_person or update_person_alias. It also does not state when not to use it or mention alternatives. The behavioral note about force=true is a rule, not a usage guideline.

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