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

Annotations already declare destructiveHint=true, idempotentHint=true, and readOnlyHint=false. The description adds a useful non-terminal constraint, but does not explain effects on the task, required permissions, or what happens after cancellation. It is consistent with the annotations and adds some value beyond them.

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?

The description is a single, front-loaded sentence with no wasted words. It immediately states the action and scope, making it easy to scan and parse.

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?

Although annotations cover the safety profile and an output schema exists, the description is too thin for a destructive cancellation tool. It omits parameter guidance, access_token semantics, side effects, and post-cancellation behavior, leaving important context to inference.

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%, and the description mentions no parameters at all. It does not explain the required task_id format or the role of access_token, so it fails to compensate for the missing schema descriptions despite having two parameters.

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 states a specific verb+resource combination: 'Cancel' an 'expert task.' It also adds the scope qualifier 'non-terminal,' which helps distinguish the operation from terminal-task handling. It does not explicitly differentiate itself from siblings like continue_expert_task or get_expert_task, but the action is clear.

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 phrase 'non-terminal' gives an implied precondition for use, but the description does not state when to choose cancel versus alternatives such as continue_expert_task, get_expert_task, or request_expert_answer. Usage is inferable, but no explicit routing guidance is provided.

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