Say a task should not be done

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

With no annotations, the description carries the full burden and does substantial work: it discloses that nothing is dropped, the task stays open and marked, unticked steps don't block it, and the claim is advisory ('only your word'). What's missing is how the mark is removed or what the person sees on their side.

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 core action and its non-destructive nature are front-loaded, and every sentence carries information. The folksy phrasing ('since it is only your word', 'takes the mark off') costs some clarity but not much length.

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, side effects, scope, and repeat-use behavior adequately. Only the downstream visibility of the mark and its removal path are left implicit.

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 schema. The description adds only marginal semantics — scope ('on any task, the person's too') and the repeat-use rule — without new detail on `body` or `task` beyond what the schema provides. Baseline 3 applies.

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 names a specific verb and resource — declaring a task won't be done — and clarifies that this is a statement, not a state change. It implicitly contrasts with `say_done` and explicitly routes follow-ups to `note`, but never names `say_done` or `unplan` as the counterpart, so sibling differentiation is inferred rather than stated.

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 a clear trigger ('it no longer matters, something else made it moot') and an explicit alternative for later information ('what is new after that goes in `note`'). The one-shot rule ('Say it once') is a real usage constraint. It stops short of stating when to prefer `say_done` or `unplan` instead.

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