Say a task is finished

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

With no annotations, the description carries the full behavioral burden and does so: it discloses refusal when a step remains open, clarifies that the task stays open and marked rather than closed, and says to call it once. These are exactly the side effects and constraints an agent needs.

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 front-loaded with the action, then adds prerequisites, refusal behavior, state effect, and alternatives. Every sentence contributes operational information, with no 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 two-parameter tool with no annotations and no output schema, the description covers purpose, timing, prerequisites, refusal, state persistence, and sibling routing. It is complete enough for correct 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 coverage is 100%, so both parameters are already documented in the input schema. The description does not add syntax or format detail for `task` or `body`; baseline 3 is appropriate when the schema does the parameter-level work.

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 action: saying a task is done, with the key caveat that it marks rather than closes the task. It distinguishes the operation from `say_not_doing` and `note`, so an agent can identify its role without opening the schema.

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 gives explicit timing (in the turn the work ends), scope (tasks you did yourself or the person's tasks), prerequisites (all steps ticked or said done first), refusal conditions, and an alternative (`say_not_doing` for reading that no longer matters). This leaves little to inference.

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