task.finish

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

Annotations already carry destructiveHint=true, so the bar is lower; the description adds that this is a state transition to COMPLETED and implies no process termination or commit happens here. It does not explain irreversibility or downstream effects of finishing, which would be useful for a destructive operation.

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?

One sentence with no filler; the key action and precondition are front-loaded. Every word earns its place.

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 tool with no output schema, this is nearly complete: it names the action, target, and required precondition. A brief note on what happens once completed—such as that the task can no longer be resumed—would fully close the loop with siblings like task.resume.

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 only one parameter, task_id, and schema description coverage is 0%; however, the description's reference to 'an ACTIVE Task' makes the parameter's meaning obvious and clarifies it must identify an active task. No format details are needed for this single self-describing identifier.

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 ('mark'), resource ('ACTIVE Task'), and target state ('COMPLETED'), which clearly differentiates it from siblings like task.cancel and task.cleanup by the resulting state. The precondition 'after processes stop and the worktree is committed' further anchors its role.

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 says to invoke after processes stop and the worktree is committed, giving the key temporal condition. It does not name alternatives such as task.cancel for abandoned tasks or task.resume for unfinished work, so the when-not-to-use guidance is implicit rather than explicit.

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