campaigns

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

With no annotations, the description carries the full behavioral burden and does disclose real traits: paced delivery, pause/resume/cancel control, and the important default that on_missing_variable=fail rejects at create time while skip leaves the literal `{token}` in the send. It is silent on permissions, whether cancel affects already-queued messages, and idempotency of create, which matter for a bulk-send mutation.

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 action list, then template semantics, then examples — a sensible order for a multi-action tool, and the per-action bullets are terse. The token-resolution paragraph is dense but every sentence carries information an agent needs to compose a valid `text` value.

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 10-parameter, six-action tool with no annotations and no output schema, the definition covers the create path well and the control actions adequately. It still leaves `skip`/`limit` unexplained and gives no sense of what list or get returns, so an agent cannot fully plan a listing flow from the description alone.

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 0%, so the description must compensate, and it largely does: name, audience_id, text, media_url, media_caption, campaign_id, and on_missing_variable are all given meaning, including the non-obvious fail/skip trade-off. The two pagination-ish parameters `skip` and `limit` are never mentioned, leaving the compensation incomplete.

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 — scheduling audiences for paced bulk delivery — and enumerates all six actions with one-line definitions, so an agent knows exactly what surface it covers. It does not differentiate itself from the sibling `scheduled_messages` or `audiences` tools, which is the only thing keeping it from a 5.

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?

Each action is described with enough context to pick the right one (create needs name + audience_id, pause/resume/cancel operate on a campaign_id), and two worked examples show realistic invocations. However there is no guidance on when to use this tool versus `scheduled_messages`, no prerequisites, and no statement of what cannot be done here.

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