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

Goes well beyond the destructiveHint/idempotentHint annotations by spelling out exactly what happens to recipients (already-delivered keep it, nobody else receives it), that drafts get nothing sent, that cancelled emails cannot be rescheduled, and that the Schedule and publish permission level is required. This is the kind of detail an agent needs before firing a destructive call.

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 core action, then mode semantics, then the permission prerequisite. The phrasing "By default one that has not started going out turns back into a draft" is slightly convoluted, but no sentence is filler.

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 two-parameter destructive mutation with annotations covering the safety profile and no output schema, the description supplies outcome semantics, irreversibility, and auth requirements. Only minor gaps remain, such as error behavior for an invalid campaignId or an already-cancelled email.

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 0%, so the description must carry the load: it explains "unschedule" and "cancel" semantics and implies "auto" via "By default." campaignId is left untouched, but its role is self-evident from the name and the regex-constrained format is in 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?

"Stops an email" gives a specific verb and resource, and the body clarifies that the target is a scheduled/sending campaign (draft-revert vs in-flight cancel). It does not explicitly distinguish itself from near-siblings like postfjord_cancel_post or postfjord_schedule_campaign, so the agent must infer by resource type.

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 effectively documents when each mode applies: default/'auto' reverts unstarted emails to draft and cancels in-flight ones, "unschedule" only reverts, "cancel" always cancels. It gives the consequences that drive the choice but never states when not to use this tool in favor of a sibling.

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