Create batch

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

Adds real behavior beyond annotations: nothing is charged, the batch is a draft, Pirate Ship splits it into rate groups (domestic small/big/heavy/international), and unratable rows are counted in errors rather than failing the call. Annotations already cover the safety profile (destructiveHint=false, openWorldHint=true), so this is strong supplementary context; omitted are duplicate-handling/concurrency and the response shape.

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 dense sentences, front-loaded with the core purpose and the follow-up call, then the inheritance/override rule, then caveats. Every clause carries information, though the third sentence packs errors/get_batch/delete_batch tightly enough to read as a run-on.

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 an 11-parameter creation tool with no output schema and 36% coverage, the description supplies the missing workflow context (create → buy_label → get_batch/delete_batch) and implies the return contains rate groups and an errors count. It does not state what identifier comes back to use with get_batch/buy_label, which is the one remaining gap an agent must guess at.

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?

With only 36% schema coverage, the description carries the load and does so for the hardest part: the package (packaging, weight_oz, size, or package_preset_id) applies to every shipment while a recipient's own weight_oz or size overrides it, and the 500-recipient cap. It says nothing about signature, insured_value_usd, or the per-row extras like rubber_stamp_1, leaving several parameters documented only by their bare types.

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 opening sentence states a specific verb and resource ('Unpaid draft batch for many packages') plus the creating-mechanism ('Pirate Ship's spreadsheet upload'), which lets an agent separate it from the order-driven sibling create_batch_from_orders without opening the schema. It stops short of naming that sibling explicitly, so differentiation is inferred rather than stated.

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 lifecycle: create the draft, buy it with buy_label (one rate_id per rate group), inspect failures with get_batch, discard with delete_batch. It communicates the context (many packages from your ship-from address) but offers no explicit 'use this instead of create_batch_from_orders when...' exclusion.

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