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

Annotations already declare readOnlyHint and destructiveHint=false, and the description adds real context beyond them: it describes the return shape (per-service batch total plus per-shipment price), that address-problem shipments are listed separately and skipped until fixed, and the required Cotlet API key/app access. Only pagination or error semantics are left unaddressed.

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 purpose, then value, then caveat, then auth. Slightly conversational ('like Get Rates with all rows ticked', 'Nothing is bought') but each sentence contributes distinct 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?

With no output schema, the description carries the burden of describing returns, and it does ('each service with its total for the batch and the price per shipment'). Combined with the skip-until-fixed note and auth requirement, an agent has enough to call it correctly; only rate-blocking/error responses are unmentioned.

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% and the schema already documents batch_id as 'Batch ID from create_batch.' The description adds no parameter-level detail beyond what the schema provides, so the baseline 3 applies.

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 resource ('Rates for every shipment in a batch') and disambiguates from the sibling get_rates via the analogy 'like Get Rates with all rows ticked.' An agent can distinguish it from get_rates, create_batch, and buy_batch without opening a 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?

The 'like Get Rates with all rows ticked' analogy tells the agent when this applies (batch-level rate lookup) and 'Nothing is bought' signals it is not buy_batch. No explicit when-not or prerequisite for callers, but the selection context is clear.

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