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

Annotations already mark the tool as destructive, so the description adds value by narrowing behavior: only pending/running jobs are cancellable, other states are rejected, and viewer-role callers cannot invoke it. It also introduces the 'cooperative' nuance, which conveys a graceful cancellation process rather than a hard kill. This exceeds the structured annotation coverage.

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, front-loaded with the action and target, and immediately followed by the two key constraints (state and role). No filler or redundant restatement of the tool name.

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?

A single-parameter cancellation tool is well-covered by the state and role constraints in the description. Given the destructiveHint annotation, the risks are clear. It could improve by stating what a successful cancellation means for the job's resulting state, but it is adequate for invocation.

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%, with the only parameter already described as 'Replay job ID'. The description does not add param-level detail such as format or origin. This matches the baseline for fully covered schema.

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?

Description states a specific verb ('cancel') and resource ('replay job'), and further scopes to 'PENDING or RUNNING' states, setting it apart from replay list/start/status tools. 'Cooperatively' adds a nuance of graceful cancellation. This is clear and specific.

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 says 'PENDING or RUNNING' can be canceled and 'Other states are rejected,' which tells the agent when it should not be invoked. It also gives a role-based precondition ('VIEWER role cannot cancel'), but it does not explicitly name alternatives or when to prefer a different replay tool.

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