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

Annotations already declare readOnly, non-destructive, idempotent, and closed-world behavior, so the safety profile is covered. The description adds meaningful context beyond annotations: it returns an exact preview plus a five-minute confirmation token and does not apply the change. Token expiry and the confirmation requirement are useful behavioral details.

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 short sentences, all front-loaded and purposeful. The first states the action, the second the confirmation requirement, the third the return value and non-effect. No repetition or 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?

Given a simple one-parameter preview tool with rich annotations and no output schema, the description covers the key gaps: what is returned (exact preview plus token), the confirmation requirement, and the absence of side effects. The main omission is parameter semantics, which prevents a perfect score.

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 0%, and the single nested input object has three fields (invoice_id, flag_type, field) with no descriptions anywhere. The description only says 'a warning' and gives no guidance on what invoice_id, flag_type, or field mean or how they identify the warning. With low coverage, the description should compensate but does not.

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 action and resource: preparing removal of acknowledgement from an invoice warning so it becomes visible again. It also clarifies the preview nature, distinguishing it from the actual mutation sibling unacknowledge_invoice_warning. However, it doesn't explicitly name the sibling or the corresponding apply tool, leaving a small inference step.

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?

The two-step flow is clear: 'Requires confirmation' and the tool returns a five-minute confirmation token while explicitly not applying the change. This tells an agent when to use it (before the real mutation) and what not to expect. It stops short of naming the follow-up tool or stating exclusions.

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