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

Annotations only declare write/non-destructive/non-idempotent; the description goes further by disclosing the no-side-effect storage semantics and the attribution default (added by the API key's contact unless source_contact_id is given). These are exactly the behaviors an agent cannot infer from the structured fields.

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, front-loaded with 'WRITE:' so the mutation nature registers immediately, and every clause carries payload (scope, no-send caveat, attribution default). No 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?

For an 8-parameter mutation with annotations but no output schema, the description covers the important unknowns: side effects and record ownership. It does not say what comes back (e.g. the new activity id) or that each call creates a distinct record given idempotentHint=false, which leaves 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 coverage is 100% and every parameter already carries a description, including the source_contact_id default and the with_contact_ids meaning, so the description's restatement adds little. The mention of with_contact_ids and source_contact_id is consistent but not additive enough to exceed the baseline.

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 and capped scope ('WRITE: records ONE activity') plus the resource kind (meeting, phone call, e-mail), which separates it cleanly from civicrm_list_activities and civicrm_add_contact_note. The 'with one or more contacts' clause pins down the relationship the record establishes.

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?

Makes the key when-not explicit: an Email-type activity only stores the record and does not send mail, so an agent won't call this expecting delivery. It gives clear creation context but never names a sibling to use instead (e.g. civicrm_list_activities for reading, civicrm_get_fields for valid type names is only referenced from the schema).

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