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

With destructiveHint=true and readOnlyHint=false already declared, the description does add two pieces of context annotations cannot convey: a $0.10 cost and an API-key requirement. However, for a destructive mutation it never says what is actually changed or whether the change can be undone, and nothing points at restore_change as a recovery path, which is a notable omission given the sibling exists.

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?

Two short clauses, front-loaded with the verb and the primary identifier; the price and auth note are tucked at the end. Nothing is wasted, though the extreme terseness is partly the cause of the parameter and safety gaps rather than pure economy.

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 need not be described, but for a destructive, priced mutation with three required parameters the description is thin: it omits the effect of applying, reversibility, and the meaning of candidate_hash/request_id. An agent could invoke it with a valid preview_id yet fail or mis-call because the other required inputs are unexplained.

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 25% and the description documents just one of four parameters (preview_id). The two other required parameters, candidate_hash and request_id, plus the idempotency_key alias relationship, carry no explanation of format, provenance, or why candidate_hash must be supplied alongside preview_id. This is a real gap for a tool where all three required values must be produced correctly.

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 ('Apply') and its object ('a normalize_people_preview by preview_id'), which cleanly pairs with the sibling normalize_people_preview and shows this is the commit step of a preview/apply pair. It does not, however, contrast itself against other write siblings like merge_people or commit_life_update, so differentiation is only partial.

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 pairing with normalize_people_preview is implied by 'Apply a ...preview', but there is no explicit when-to-use statement, no prerequisite that a preview must exist first, and no guidance on when to abandon the preview instead of applying it. Alternatives are not named.

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