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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds real value beyond that by clarifying this is a guidance-only artifact generator with no file reading, rate fetching, scheduling, or booking side effects — a meaningful behavioral boundary the annotations alone don't express.

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?

Two tight sentences: outputs and scope first, exclusions and usage trigger second. No filler, and the most decision-relevant content (what you get, what it is not) is front-loaded.

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?

There is no output schema, yet the description identifies the return payload (CSV headers plus starter prompt), which is the key thing an agent needs. For a one-parameter, read-only helper it is nearly fully specified; only the exact shape of the returned prompt/headers goes unstated, which 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?

Schema description coverage is 0% and the single `workflow` param is an enum, so the description must supply meaning — it does so by naming the three scenarios. However, the wording ('shipment quoting') does not line up exactly with the enum value `shipment_intake`, leaving a small mapping ambiguity for the caller.

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 and concrete artifacts (shipment intake CSV header, results CSV header, starter prompt) and enumerates the three supported workflows. The clause 'Guidance only: does not read files, fetch rates, schedule work, or book' cleanly separates it from the quoting, booking, and tracking siblings.

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?

'Use this when an operator asks how to start or supplies invoices/a shipment sheet' gives a clear triggering condition, and the negation list ('does not read files, fetch rates, schedule work, or book') tells the agent when to route elsewhere. It stops short of naming a specific sibling to use instead once the operator moves past setup.

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