mailkite_stop_sequence

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

Annotations already indicate this is not read-only, not idempotent, and not destructive, but the description adds valuable context: it always returns 200 with a count, so it is safe to fire blindly. It also clarifies that cancelKey stops every in-flight run carrying it, which is a behavioral trait beyond the schema. The only minor gap is that it doesn't explicitly state what the count represents, but the 'safe to fire blindly' note is a strong behavioral disclosure.

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?

Three sentences, each earning its place: the first explains the two invocation modes, the second covers the safe-to-fire behavior, and the third states the auth requirement. The most important operational guidance is front-loaded, and there is zero 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 tool with no output schema and no required parameters, the description covers the key decision (which parameter path to use), the safety profile (always 200), and the auth requirement (mk_live_… key). It doesn't describe the exact response shape beyond 'a count,' but given the tool's simplicity and the absence of an output schema, this is a minor gap. The description is complete enough 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 the schema already documents all three parameters. The description adds meaning by explaining the relationship between cancelKey and the sequence+email pair, and by clarifying that cancelKey is the caller's own invoice/order id rather than a Mailkite-internal id. This goes beyond the schema's field descriptions and helps the agent understand the two mutually exclusive invocation modes.

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 clear, specific verb and resource: 'Stop whatever is chasing someone.' It distinguishes itself from sibling tools like mailkite_cancel_enrollment and mailkite_delete_sequence by focusing on stopping in-flight sequence runs via a cancelKey or sequence+email pair. The title 'Stop Sequence' is reinforced with concrete operational detail, so an agent can tell this apart from related tools.

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 explicitly states when to use each parameter path: pass cancelKey if you set one, or pass sequence and email together if you did not. It also notes the tool is safe to fire blindly from a webhook because it always answers 200 with a count. This is strong usage guidance that tells the agent exactly how to choose between the two invocation modes.

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