task_done

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

Goes well beyond the annotations by disclosing what `verify` actually does — runs the command in the project root, exit 0 archives the task, failure or omission leaves it resolved-but-unverified and visible to the human. It also describes the return shape (id, state, resolution as JSON). This is exactly the kind of side-effect context annotations (readOnlyHint/destructiveHint false) cannot convey.

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 tight sentences, front-loaded with the primary action and consequence before the fallback routes. No filler; every clause carries either behavior, routing, or return-value information.

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?

No output schema exists, but the description explicitly states what is returned (id, state, resolution as JSON), and it covers the mutation's side effects, the verify lifecycle, and escalation paths. Nothing an agent needs to call this correctly is missing.

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%, so the baseline is 3, but the description adds real meaning the schema does not: the behavioral consequence of `verify` (archival on exit 0 vs. unverified state on failure) and that `diffRef` is surfaced to the reviewer. `id` and `model` are left to the schema, hence not a 5.

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?

Specific verb+resource ('mark a task resolved ... recording how') and it explicitly names the sibling tools it is not (task_fail, task_block), so an agent can route without opening a schema. Clearly differentiated from the browser_* and review_* siblings.

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?

States the trigger (once your change addresses it), the alternatives by name, and the selecting condition for each: task_fail if the attempt didn't work, task_block if you need the human. When/when-not is fully spelled out.

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