shipment_summary

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

Annotations already carry readOnlyHint/idempotentHint/destructive=false, and the description adds substantial behavior beyond them: the 2.40 m loading-metre divisor, 'no stackable flag treated as NOT stacked', palletSpaces as floor positions versus palletRows, partial failures surfacing in warnings instead of failing the call, the 25 requests/day IP rate limit with 429 retry_after_seconds and Retry-After header, and the legacy camelCase result shape. No contradiction with annotations.

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?

Long (~350 words) but front-loaded: the first sentence states the entire scope, followed by clean Inputs/Behavior/Returns/Limitations/Related sections. Some redundancy exists (engine calls and pallet floor positions appear twice), but for a composite tool merging three engines across four modes, dense detail is warranted rather than waste.

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 7-parameter, 4-mode composite with nested objects and an output schema, the description is complete: all input semantics, mode-specific conventions, error/rate-limit handling, return shape summary, limitations ('planning summary, not a quotation or compliance determination'), and sibling routing are covered. The existence of an output schema excuses full return-value enumeration.

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 coverage is 100%, so the baseline is 3. The description adds relational meaning beyond individual field docs: 'origin/destination and incoterm refine the duty leg,' the conditional enabling of sections (hs_code + customs_value → duty; un_number → DG), and a compressed statement of the items[] field set and units. This is a modest but real increment over the schema.

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?

Opens with 'Composite shipment analysis in one call' and itemizes every computation: CBM, gross/chargeable weight, road LDM with pallet spaces and vehicle suggestion, volumetric weight, revenue tonnes with container suggestion, DG presence, and UK duty. The specific resource and scope are unmistakable, and the Related section hard-distinguishes it from the single-purpose 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?

Explicitly names alternatives and their relationship: consignment_calculator (canonical snake_case lines[] shape with advisory flags), the three engines it actually cals (ldm_calculator, adr_lookup, uk_duty_calculator), and 'the rest are the single-purpose equivalents of arithmetic it does inline.' Also routes to get_subscribe_link for higher rate limits. When-to-us vs alternatives is fully stated.

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