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

Annotations already provide idempotentHint=true and destructiveHint=false, but the description adds meaningful behavior beyond those hints by specifying that only unsent deliveries are cancelled and that the endpoint must be account-owned. This clarifies the side-effect boundary in a way the schema and annotations alone do not.

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 a single, front-loaded sentence with no filler. Every phrase adds value: idempotency, ownership, the stopping action, and the cancellation scope are all expressed in eleven words.

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 simple one-parameter mutation tool with no output schema, the description covers the essential context: what is stopped, who owns it, idempotency, and exactly which deliveries are affected. It does not detail response behavior or explicitly state that already-sent deliveries are preserved, but the 'only unsent' phrasing sufficiently implies this.

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 description coverage is 0%, so the description carries the burden of explaining the parameter's meaning. It does this indirectly by describing the target as an 'account-owned endpoint' and referencing 'its unsent deliveries', which adds semantic context to endpointId. However, it never explicitly names endpointId or states it is the identifier of the endpoint to stop, leaving some inference required.

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 identifies a specific action ('stops'), a specific resource ('account-owned endpoint'), and a precise behavioral scope ('cancels only its unsent deliveries'). It clearly distinguishes this from sibling tools that create, register, verify, or list endpoints.

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 provides clear context for when to use the tool: when an account-owned endpoint needs to be stopped. The 'only its unsent deliveries' clause also sets an explicit boundary about what will and will not be affected, though no alternative sibling tool is named.

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