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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the write/destructive profile is covered structurally. The description adds real behavioral context beyond that: cancellation is cooperative, is state-gated, and is blocked for VIEWER role — auth and eligibility facts an agent could not infer from the annotations.

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, front-loaded with the action and its scope, followed by the state rejection rule and the role restriction. No filler or redundancy.

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 key eligibility and permission facts are present. It omits what the final job state becomes and whether already-processed windows are retained, which would fully close the loop on a destructive operation.

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?

There is a single parameter with 100% schema description coverage, so the schema already carries the meaning of jobId. The description only reinforces that the ID refers to a replay job, adding no format, sourcing, or lookup guidance beyond the 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?

The description gives a specific verb ('cancel') and resource ('window replay job'), plus the state scope where it applies. It does not explicitly distinguish itself from the sibling lexq_simulation_cancel, but the replay-vs-simulation naming keeps them separable.

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?

It clearly states the conditions under which cancellation is valid ('PENDING or RUNNING') and that other states are rejected, which tells the agent when not to call it. It stops short of naming an alternative tool or what to do instead when the state is invalid.

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