rename_person

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

Annotations already declare destructiveHint=true and idempotentHint=false; the description adds context annotations cannot express — the old value is not lost but retained as a `former_name` alias, or as a `handle` when it looks like an email, and still feeds import matching. It also discloses two named failure modes (`name_is_email`, `name_conflict`), which is precisely the non-obvious behavior an agent needs before invoking a destructive tool.

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 behavior statement is front-loaded in the first sentence, with the usage guidance and failure modes following in a logical order. The rationale clause ("so it is still contact information and imports still match on it") is slightly discursive but justifies why the alias retention matters, so it 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?

For a two-parameter destructive mutation with no output schema, the description covers the key question — what happens to the previous name — plus the refusal conditions. Gaps remain around success response shape and whether any permission or preconditions apply, but nothing essential to calling 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?

Schema coverage is 0%, so the description carries the burden. It adds real constraints on the `name` parameter (an email address is rejected as `name_is_email`; a name owned by another person is rejected as `name_conflict`), but says nothing about `person_id` — its expected form, how to obtain it, or what happens if the person is unknown.

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 opening clause names a specific verb and resource — "Replace a person's canonical name" — and immediately contrasts it with alias handling ("the old name stays on as an alias"), which is exactly what separates it from siblings like add_alias and update_alias. There is no ambiguity about what state changes.

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?

It gives an explicit when-to-use condition: correcting a wrong name, with the concrete example of an email address stored as a name. It does not state when NOT to use it (e.g. when the value is merely an alternate rather than a correction, which should go to add_alias), so the routing guidance stops just short of complete.

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