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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=true, and the description still adds real behavioral context: state-dependent effects, that an already-ended campaign is returned unchanged (making the call effectively a no-op there), and that only unsent mail is halted while submitted mail still delivers. That last detail is materially important for a destructive operation and is not inferable from the annotations.

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?

Two dense sentences, front-loaded with the core action and followed by state outcomes and the delivery caveat; every clause carries information. The 'ends as with dealmachine_mail_campaign_end' phrasing is slightly indirect but not wasteful.

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?

No output schema exists, and the description implicitly indicates a campaign object is returned ('returned unchanged'), while covering the destructive consequences an agent needs before confirming. It omits permission/auth requirements and any billing or wallet-charge implications, which are the main remaining gaps for a destructive mutation.

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 50%: 'confirmed' is well documented in the schema as a user-approval gate, while 'campaign_id' has no description. The description adds nothing about either parameter — not the approval requirement, not the ID format — so it neither compensates for the gap nor adds value over the schema.

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 and resource ('Cancels a mail campaign') and immediately distinguishes its semantics from the sibling dealmachine_mail_campaign_end by outcome per campaign state. The 'kept for existing clients' note also signals legacy status, so an agent can tell it apart from end/pause/resume without opening a 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?

Gives clear state-based context for what happens when invoked (started, draft, already-ended) and names the equivalent sibling for started campaigns. It stops short of an explicit routing rule such as 'prefer mail_campaign_end for new work', so the alternative selection is implied rather than prescribed.

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