Cancel campaign

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

Annotations declare destructiveHint=true and idempotentHint=true, but the description adds behavior they cannot express: cancellation is partial (only unreached recipients stop, delivered mail cannot be recalled) and on v0.15+ the campaign reverts to an editable draft that can be fixed and resent. That post-state information and the v0.15+ version caveat are exactly the extra context that annotations omit.

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?

Bold-labelled sections are front-loaded and easy to scan, and every section is relevant. Minor redundancy: the recall limitation appears twice, once in Purpose ('Mail already delivered cannot be recalled') and again in Note ('delivered mail cannot be recalled'), which is a small but real duplication in a short description.

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 single-parameter mutation with no output schema, the description covers purpose, exclusion, expected return (confirmation of cancellation), triggering conditions, and the important partial-effect and draft-reversion behaviors. An agent has everything needed to decide and call 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?

There is a single parameter (id) with 100% schema description coverage ('Campaign UUID'), so the schema already carries the semantics. The description adds no format, sourcing, or lookup guidance beyond what the schema provides, which is the baseline-3 case when the schema does the heavy lifting.

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 ('Stop a scheduled or in-flight campaign') and immediately bounds the scope with 'Mail already delivered cannot be recalled.' It also explicitly distinguishes itself from the sibling that removes a campaign entirely (plunk_delete_campaign), so an agent can route without inspecting either 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?

The 'Not for' line names the alternative tool (plunk_delete_campaign) and the 'Use when' line gives two concrete triggering conditions (send started in error, scheduled send should no longer happen). Both when-to-use and when-not-to-use are present, leaving nothing to inference.

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