flag

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

With no annotations, the description carries the full load and does well: it discloses the side effects (review episode + edge), that the target is untouched and the doubt recorded beside it, and the lifecycle visibility until settled. It omits edge cases such as flagging a nonexistent target or repeated flags, so not quite exhaustive.

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?

Four tight sentences, front-loaded with the core action and side effect, then the non-destructive guarantee, then lifecycle, then the sibling distinction. 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?

No output schema or annotations, so the description must cover behavior and it largely does: side effects, target immutability, and where the flag surfaces. The only real hole is the undocumented `initiative` parameter.

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 67%: `reason` and `target` are described in the schema, and the description reinforces that the reason is carried into the episode. The third parameter `initiative` (nullable, default null) has no description in either the schema or the description, so the gap is not compensated.

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?

States a specific verb (flag) and the exact effect: writes a review episode carrying the reason plus a contradicts edge to the target. It names and distinguishes the closest sibling ('not the same as `link contradicts`'), so an agent can choose correctly without opening schemas.

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?

Explains when the flag shows up (in `awake`'s under-review list) and how it is cleared (`close_review` or `resolve`), plus the explicit contrast with `link contradicts`. It stops short of stating when not to flag at all, but the alternative-routing is clear.

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