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

Annotations already cover the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=true), so the description's job is to add context — and it does: completed steps stay done and billing is prorated to what was used. That tells the agent cancellation is partial and non-reversible in the 'un-finish' sense, which annotations alone do not convey. It omits what happens if the job has already finished or failed.

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 short sentences with the action and identifier front-loaded, followed by the side effects the caller cares about. Every sentence carries information; the only slight softness is 'charged only for what it used', which is qualitative rather than precise.

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 two-parameter cancel tool with no output schema, the definition covers what it does, when to use it, what survives, and what it costs — enough to call it correctly. The remaining gap is outcome behavior on already-terminal jobs, which idempotentHint only partially covers.

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 100%, so the schema already documents both jobId and projectId, including the null/default behavior for projectId. The description only restates jobId's origin from start_routine and adds nothing about projectId or identifier format, so the baseline 3 applies.

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 ('Stop a routine that is running') and pins the identifier semantics by tying jobId back to the output of start_routine. It is immediately distinguishable from the sibling start_routine and from wait_for_jobs, so an agent can pick the right counterpart 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 an explicit positive condition ('person changed their mind or the routine is no longer needed'), which implicitly rules out cancelling work that is still wanted. It stops short of naming the alternative for the opposite case (letting the job finish and calling wait_for_jobs), but the routing intent is clear.

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