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

Goes far beyond the annotations (readOnlyHint=false, destructiveHint=true, idempotentHint=true): it discloses the notification the assignee receives, that Google Calendar gets the event and Google emails an invitation to the linked contact, who counts as that contact, and that the tool cannot add other attendees. It also explains idempotencyKey retry semantics and warns that CRM field values are untrusted data — a genuinely valuable safety disclosure.

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 core action is front-loaded and the paragraph is dense with non-redundant facts — assignment default, notification, calendar side effects, idempotency, trust boundary. It is longer than typical, but nearly every clause carries operational meaning; the only soft spot is the loosely connected final security sentence.

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 12-parameter mutation with external side effects and no output schema, the description covers the consequential behavior: side effects on Google Calendar/email, notification fan-out, assignment defaults, idempotency, and untrusted-content handling. It stops short of describing what is returned on success and leaves several parameters unexplained, which keeps it out of the top band.

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 8%, so the description must carry the load, and it does explain the two highest-risk parameters: assigneeId (defaults to you, must come from list_record_owners) and idempotencyKey (fresh per activity, retry returns the first result). But location, durationMin, description, and objectType get no explanation, leaving a meaningful share of the 12 parameters undocumented.

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 resource ('Creates a task, call or meeting, optionally linked to one record'), which tells the agent exactly what is produced and that the type is one of three kinds. It does not, however, distinguish itself from the sibling create_task, which an agent could easily confuse with creating a TASK-type activity.

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?

Gives real usage conditions: only schedule or assign on the user's instruction, assignment defaults to the caller unless assigneeId names another member, and it explicitly names list_record_owners as the source of valid assignee ids. It also rules out one behavior ('You cannot add other attendees here'), though it never contrasts itself with create_task or update_activity.

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