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

With no annotations, the description carries the full burden of behavioral disclosure. It thoroughly explains idempotency (replaying the same key returns the same campaign and produces no second dispatch), the one-time freeze, and that consent, suppressions, and audience membership are evaluated at freeze time. This goes well beyond a basic 'launches a campaign' and gives the agent a clear mental model of side effects and guarantees.

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 description is three sentences, each earning its place. The main action is front-loaded, followed by the critical freeze behavior and the idempotency guarantee. No fluff or repetition; every clause adds 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 launch tool with no output schema, the description covers the essential behaviors: idempotency, freeze timing, and what gets sent. It does not mention error cases (e.g., campaign not found, invalid state) or required preconditions (e.g., campaign must exist), but these are often expected to be handled generically. The freeze and idempotency details are sufficiently complete for an agent to call it correctly.

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%, so parameters already have descriptions. The description adds meaningful context for the idempotency_key by explaining its replay semantics (returns same campaign, no second dispatch) and clarifies that scheduled_for controls scheduling versus immediate launch. This goes beyond the schema's one-line descriptions and enriches understanding, though it does not enumerate each parameter explicitly.

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: 'Freeze and launch or schedule a campaign idempotently.' It clearly states what the tool does (launches or schedules a campaign) and distinguishes it from sibling tools like campaign_create (creation), campaign_get (retrieval), and campaign_update (modification). The freeze semantics add specificity, leaving no doubt this is the launch action.

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?

The description implies when to use this tool (when launching or scheduling a campaign) but does not explicitly contrast it with alternatives or state conditions like 'use this instead of campaign_update' or prerequisites such as the campaign must exist. The 'launch or schedule' wording covers both immediate and delayed dispatch, but there is no explicit guidance on choosing between them beyond the scheduled_for parameter. This is adequate but not explicit.

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