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

Beyond the annotations, the description warns that incorrect resolution can cause duplicate or lost actions, explains that evidence must come from real verification, and notes that evidence is recorded. Annotations indicate this is not read-only or idempotent, and the description aligns with that by framing it as a consequential state-changing action.

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 a single dense paragraph with no filler. The usage guard is front-loaded, each sentence adds semantic value, and the consequence of misuse is stated in one memorable clause.

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?

The description provides enough operational context to call the tool safely: when to call, what outcome values to use, what evidence to include, and why accuracy matters. It lacks explicit guidance on the optional `result` field and what happens after resolution, but those are secondary to the core settle action.

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 description coverage is only 25%, but the description compensates for the two most important parameters: it explains the `outcome` enum values and requires verification details in `evidence`. `effect_id` is self-evident, while the optional `result` object remains unexplained, which is a minor gap.

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—recording the real outcome of an indeterminate effect—and clearly defines what 'succeeded', 'failed', and 'cancelled' mean. It also narrows the tool's role by requiring prior verification, which sets it apart from generic effect-reporting or checking tools.

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 an explicit precondition ('Use ONLY after you have checked the third-party system') and a strong prohibition ('Never guess'), so an agent knows when it is and isn't appropriate to call. It does not name sibling alternatives, but the when/when-not boundary is otherwise clear.

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