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

Annotations only give the generic safety profile (readOnlyHint=false, destructiveHint=false, non-idempotent); the description adds real behavioral content on top: completed work is not reverted, the outcome is reported back, and the operation 'marks cancellation' rather than hard-deleting. The scope/risk/effects line reinforces the low-risk, reversible-ish nature without contradicting the annotations. It stops short of explaining latency or what happens on a second call (non-idempotency is only implied).

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 sentences covering the action, the state distinction and the irreversibility caveat, plus a compact metadata line — front-loaded and essentially waste-free. The scope/risk/effects stamp is slightly boilerplate but cheap.

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 one-parameter mutation with no output schema, the description covers what happens (pending vs running), what is not affected (completed work), and that the response reports what was applied. The remaining gap is the identifier parameter's meaning, which is the one thing an agent could get wrong.

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?

The single required parameter 'id' has 0% schema description coverage, and the description never mentions it or clarifies whether it is a job id, a reservation id, or a name. With low coverage the description is expected to compensate, and here it does not at all.

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 ('Cancela um job') and goes further by splitting the semantics into pending jobs (cancel) versus running jobs (request a stop), which is exactly the distinction an agent needs. It is clearly not a read tool, so it separates itself from get_job/list_jobs, but it never names a sibling or a related tool explicitly.

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?

Usage is implied by the state-based phrasing (pending → cancel, running → request stop), and the caveat that already-completed work is not undone tells the agent one situation where calling is pointless. There is no explicit guidance on when not to use it or what alternative exists if the job is already finished.

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