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

Annotations already declare non-read-only, non-destructive, non-idempotent, so the safety profile is covered; the description adds genuinely new behavioral context by establishing that creation yields an inert draft and that outbound activity requires a separate launch. It does not disclose validation behavior, whether creation can fail on number/consent mismatches, or permission requirements, which keeps it from a 5.

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 purpose and the critical launch caveat are front-loaded, and the whole definition is two sentences with no filler. The middle sentence is a long comma-run list that is dense to parse but each element carries information.

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 7-required-parameter mutation with nested objects, 22% schema coverage and no output schema, the description covers the conceptual surface but leaves real gaps: it never says what is returned (presumably a campaign id needed for launch_campaign) or how concurrency/reserved_concurrency and time_zone_mode interact. Adequate to attempt a call, not complete enough to call confidently without opening the schema.

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 22% schema coverage across 18 parameters and nested objects, the description usefully names the major configuration groups and spells out the consent_basis values and the three retry_policy presets. However, it says nothing about the distinction between max_concurrency and reserved_concurrency, time_zone_mode, language, ends_at, organization_id scoping, or the shape of retry_policy — leaving several parameters undocumented in both places.

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+resource+state ('Create a draft outbound campaign') and then enumerates exactly what the draft configures: agent, caller-id numbers, contact list, purpose, consent basis, calling windows, retry policy, concurrency, schedule. This is clearly distinct from launch_campaign, update_campaign, and get_campaign in the sibling set.

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 explicitly states the lifecycle boundary: the campaign does not run until 'launched with launch_campaign,' which routes the agent to the correct follow-up tool. It gives no guidance on when to prefer update_campaign for an existing campaign or on prerequisite policy checks (evaluate_outbound_policy / authorize_outbound), so it stops short of full alternative coverage.

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