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

Adds real context beyond the annotations: nothing is charged until buy_label, Pirate Ship splits rows into domestic small/big/heavy/international rate groups each needing its own rate_id, and unrated rows are surfaced as errors. The 500-recipient cap and per-recipient override rules are also disclosed. It does not reconcile itself with destructiveHint=true, though the 'nothing is charged / draft' framing makes the risk profile understandable.

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?

Front-loaded with the core definition, then proceeds through input mode, override rules, rate-group consequences, and lifecycle. Dense and slightly telegraphic in the opening clause, but nearly every sentence carries operational information.

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 no-output-schema, 11-parameter creation tool with many sibling batch operations, the description covers the lifecycle well but never states what the call returns (presumably a batch id plus errors) that buy_label and get_batch require. The 'errors counts rows' phrasing hints at the response shape without confirming the identifier an agent needs to chain the next call.

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 description coverage across 11 parameters, the description compensates for the most non-obvious case: the package-level packaging/weight_oz/size applies to all shipments while a recipient's own weight_oz or size overrides it, and ship-from is scoped from the account. It says nothing about signature, insured_value_usd, packaging presets, or the package_preset_id precedence, leaving several parameters documented only by terse or absent schema text.

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 resource and outcome: an 'Unpaid draft batch for many packages' that is rated by Pirate Ship and split into rate groups. It is clearly distinct from single-shipment creation, but it never names the closest sibling, create_batch_from_orders, so an agent must infer which batch-creation path to take.

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 explicit downstream routing ('buy it with buy_label', 'get_batch shows them', 'delete_batch drops the draft') and states the input mode (spreadsheet upload, up to 500 recipients). It does not say when NOT to use this versus create_batch_from_orders or create_shipment, which is the one selection decision left to inference.

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