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

Annotations already declare destructiveHint=true and idempotentHint=true, yet the description adds non-obvious behavior: only supplied fields are mutated (so unspecified data is untouched), and flipping a do-not flag to false re-enables a contact the person may have declined. That last warning is a consent-safety nuance no structured field conveys.

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?

Three tight sentences with the write nature front-loaded, the field inventory second, and the safety caveat last. No filler, and the highest-risk instruction is placed where it will be read.

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 13-parameter mutation tool with no output schema, it covers scope, partial-update behavior, and the consent hazard, which is most of what an agent needs. It leaves household_name/organization_name unexplained and says nothing about the return payload or validation failures (e.g., contact_id not found).

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?

With only 15% schema coverage across 13 parameters, the description must compensate, and it does: it names first/last name, job title, source, preferred language, and all four do-not flags plus bulk-mail opt-out, explaining what the opt-out means. It omits household_name and organization_name, which are in the schema but unmentioned, leaving a real gap given the low coverage.

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?

Opens with an explicit 'WRITE:' marker, states the verb (changes), resource (ONE existing contact), and enumerates the affected field groups, plus names the underlying APIv4 method. An agent can distinguish this at a glance from civicrm_create_contact, civicrm_get_contact, and the list_* siblings.

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 'ONE existing contact' scope plus partial-update semantics make clear this is for modifying rather than creating, and the do-not-flag caution gives an explicit when-you-should-not rule. It stops short of naming civicrm_create_contact as the alternative for new records or stating prerequisites like contact existence.

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