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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered. The description adds genuinely new context beyond the annotations: partial billing ('pay only for steps already finished') and credit-hold release, which materially affects an agent's decision to cancel. It doesn't say whether in-flight steps are terminated or whether cancellation is irreversible, keeping it below a 5.

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 tight sentences with zero filler, and the operation scope is front-loaded ahead of the billing consequence. Every clause earns its place.

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?

Annotations cover the safety/idempotency profile and the description adds the billing consequence, so the agent has what it needs for a one-parameter mutation. Without an output schema, some return-value or terminal-state behavior (e.g., canceling an already-finished job) is unstated, but this is a minor gap.

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%, but the single parameter is job_id with an explicit uuid format and pattern, making it largely self-explanatory from the schema itself. The description adds nothing about the identifier, which is acceptable here but leaves no margin above baseline.

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?

Specific verb ('Stops') plus resource ('job') and explicit state scope ('queued, running or approval-waiting'). An agent can immediately distinguish this from siblings like get_job_status or edit_video.

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 constrains usage by naming the three job states eligible for cancellation, which tells the agent when this applies. It does not explicitly name an alternative (e.g., get_job_status to verify state first) or state what happens on an already-completed job, so it stops short of full routing guidance.

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