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

With only readOnlyHint=true in annotations, the description carries real behavioral weight: result ordering ('cheapest first'), the dedup rule ('each service level once per pickup type'), the pickup_type semantics, FedEx hard limits (108 in longest side, 165 in length+girth — not present in the schema), the 10-day pickup window, and the signed-in account requirement. This is exactly the kind of context an output-schema-less tool needs.

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?

Information-dense and front-loaded: purpose first, then result shape, then workflow, then constraints. Every sentence carries payload, though the want of an output schema forces a slightly run-on packing of return-format and limit details into one paragraph.

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?

No output schema exists, and the description compensates by describing the return shape (all FedEx options, cheapest first, per service level per pickup type) along with constraints, auth prerequisites, and the downstream booking path. An agent has enough to call it correctly and interpret the result.

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 100%, so the schema already documents all four parameters, making 3 the baseline. The description adds the meaning of pickup_type ('fedex_pickup' vs 'dropoff') — but notably pickup_type does not appear in the input schema at all, and the package-group semantics it restates are already in the schema. Net added parameter value is minimal.

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+resource ('FedEx parcel rates for small packages (boxes, not pallets), US domestic ZIPs') and immediately scopes itself away from the freight siblings (ltl_quote, ftl_quote, box_truck_quote) via the boxes-not-pallets qualifier. An agent can distinguish this from parcel_book and the freight quote tools without opening the schema.

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?

Gives a clear usage chain: quote, present options to the user, then book the chosen one with parcel_book — an explicitly named alternative. It does not explicitly say when NOT to use it (e.g. pallets -> ltl_quote, or other carriers), relying on the implicit 'boxes, not pallets' cue, so it falls just short of full when/when-not coverage.

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