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

Annotations already cover idempotency and non-destructiveness, and the description adds meaningful behavioral context: no carrier verification is wired, the buyer is notified, the buyer may dispute, and the platform auto-marks after 10 days. This goes well beyond the structured annotation data.

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 compact sentences front-load the core purpose and then efficiently cover state constraints, side effects, and platform behavior. There is no filler or redundant speculation.

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 single-parameter mutation with annotations and no output schema, the description covers the essential call context: valid states, side effects, dispute possibility, and platform fallback. It leaves the exact error behavior for non-shipped orders implied rather than explicit, but overall it is sufficiently complete.

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?

The input schema already fully documents order_id with a clear description including the no-op behavior. The tool description does not add additional parameter-level semantics, so the baseline for high schema coverage 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 states a specific verb and resource: 'Declare a shipped order as delivered', which clearly identifies the action and its target. It also differentiates the tool from adjacent operations by noting the lack of carrier confirmation and the state precondition (only from shipped).

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 description gives clear state-based guidance: it is only valid from shipped, already-delivered is a no-op, and the platform auto-marks after 10 days. It does not explicitly name a sibling alternative like seller_mark_shipped, but the usage context is otherwise well specified.

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