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

Annotations only tell the agent it is a non-readonly, non-destructive mutation. The description adds real behavioral context beyond that: nothing is launched or enrolled, intent-mode audiences self-populate and 'each waits for review first,' and the draft status should be communicated to the user. Return shape is the only omitted trait.

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-loads the essential fact (draft, no launch/enroll) and then lays out modes economically. The intent-mode sentence is long but packs distinct behavioral information that earns its place.

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 mutation tool with no output schema, the description covers creation semantics, mode selection, review gating, and draft messaging. It omits what the call returns (e.g., a campaign id), which an agent would want for a follow-up launch, but otherwise nothing needed to call it correctly is missing.

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 63%, so several parameters (name, timezone) rely on the schema alone. The description does map mode values to their parameters (preset_id, ai_brief, intent_signals) and explains the intent mode's self-filling audience, which adds meaning beyond the enum list, but it never addresses min_fit or min_tier, so it doesn't fully compensate for the coverage gap.

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+resource ('Create a draft campaign') and immediately delimits scope with 'Does not launch or enroll anyone,' which cleanly separates it from launch_campaign and enroll_prospects. An agent can pick this tool over its siblings without inspecting any schema.

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?

Enumerates the four modes (blank, preset, ai, intent) and ties each to its driving parameter, plus a clear rule: 'Tell the user it is a draft until they confirm a later launch.' It doesn't explicitly name the sibling tools to use at launch time, but the when-to-use context is strong.

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