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

Given annotations declare destructiveHint=true and readOnlyHint=false, the description earns credit for disclosing exactly what is destroyed: phones/emails/aliases/tags are replaced wholesale when passed, while add_tags/remove_tags edit in place. It also spells out null semantics for birthday and keep_in_touch_days, the effect of archived on reminders and people_due, and the confirmation policy with its reversibility claim. This is materially more than the annotations convey.

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?

Front-loaded with the core action, then field semantics packed into tight semicolon-delimited clauses that match the caller's decision order. The confirmation paragraph is the longest element but carries policy information an agent would otherwise guess wrong about, so it earns its space.

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 20-parameter destructive mutation with no output schema, the description covers mutation semantics, reversibility, and execution policy—the things the schema cannot say. Return values are only loosely characterized ('an ordinary result, not a plan_token'), and a handful of scalar fields get no explanation, leaving a small gap.

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 5% across 20 parameters, so the description must compensate, and it does for the highest-risk ones: replacement vs. additive tag behavior, null-clears for birthday, null-disables for keep_in_touch_days, snooze_until format, and the direction of the relations mapping. Several fields (note, company, how_met, starred, summary, position) remain undocumented anywhere, which keeps this below a 5.

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 a specific verb and resource plus scope: 'Change a person in the caller's OWN contact book.' That scope wording implicitly separates it from create/delete/merge siblings, though no sibling is named as an alternative the way a top-tier definition would. An agent can still identify the operation unambiguously.

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 states the operating context (own contact book, partial-update semantics: pass only fields to change) and devotes a block to when this tool fires immediately versus when other categories of action must propose and wait. It does not cover edge-case choices such as when to use merge or create instead, so guidance is clear but not exhaustive.

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