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

Beyond the annotations, the description discloses the automatic side effect of enqueuing carrier polling and explicitly states that repeating the same order/tracking pair is a no-op success. This gives the agent a clear model of the tool's write behavior and idempotency.

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 compact, uses two short sentences, and packs essential behavior (action, idempotency, side effect) without redundancy or unnecessary detail.

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?

It provides enough context for a caller to understand the action, idempotency, and background side effect, and the schema supplies the parameters. It does not specify response shape or error conditions, but with no output schema and clear side effects this is acceptable.

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 schema already covers all four parameters with meaningful descriptions, including the idempotency note on tracking_number and enum values for carrier. The prose description adds little parameter-level detail beyond what the schema provides, so it stays at the baseline for high schema coverage.

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 uses a specific verb-resource pair ('Mark an order as shipped') and identifies the key input (tracking number). It clearly distinguishes this from related tools like seller_mark_delivered or seller_attach_tracking by focusing on the shipped status transition.

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 context for when to call it—when an order should be marked shipped with a tracking number—and includes an important usage caveat about idempotency. It does not explicitly contrast this tool with sibling alternatives, but the purpose and behavior are sufficiently clear.

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