cancel_task

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

With no annotations, the description carries the full transparency burden. It discloses the state precondition and the return payload shape, but it does not mention side effects, error/conflict behavior, or the role of expected_version. These are material gaps for a mutation tool, though the description is not misleading.

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 exactly two sentences, front-loaded with the core action and state restriction, and then a useful pointer to get_task. Every word earns its place, with no repetition or filler.

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 simple cancel operation, the description covers the basic purpose and return shape, and the get_task pointer is helpful. However, the lack of parameter semantics and conflict/error behavior, combined with the absence of annotations and output schema, leaves the tool only marginally adequate for safe autonomous 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 description coverage is 0%, and the description provides no explanation of id, by, reason, or expected_version. The agent must infer meaning solely from parameter names and schema constraints, leaving important semantics like optimistic concurrency undocumented.

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 clearly states the action ('Cancel a task') and the resource (a task), and it adds a meaningful state constraint ('not already completed/approved/cancelled'). It also distinguishes itself from get_task by noting that the returned summary omits history[], which helps agents pick the right sibling tool.

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 explicitly describes the valid use case: canceling a task that is not in a terminal state. It also points to get_task as an alternative for retrieving history. However, it doesn't go further to explain when cancel_task should be chosen over other mutation siblings or what to do if the task is already claimed or in progress.

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