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

Annotations already declare readOnly/idempotent/non-destructive, and the description still adds substantial behaviour: aggregation rule (SKU, falling back to item name + variant), sort order, whole-number totals, flagging of missing or odd quantities, tick boxes per order, and dual PDF+CSV output. It also clarifies the operation is purely local reporting and does not touch store data.

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 trigger and user phrasings before the mechanics, and every sentence carries substance (inputs, aggregation, output, exclusions). It is dense and long-sentence-heavy, but there is no filler or repetition.

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?

Given six optional parameters, deep nesting, and a complex multi-source input model, the description covers what an agent must know: which input forms are accepted, how aggregation and ordering work, what the outputs are, and what the tool will not do. The presence of an output schema means return-value detail is not required.

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 goes beyond it by explaining accepted input routes for the `orders`/`file` parameters — pasted text, an image converted to order objects, or attached Shopify/Etsy/WooCommerce/Amazon exports. It does not explain `columns`, `page_size`, or `home_country`, but those are fully documented in 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?

States a specific verb and artefact ('generate a pick list') plus the exact transformation performed: sums quantity of each SKU across orders, sorted by bin location then SKU, output as PDF and CSV. It explicitly separates itself from the only sibling by naming 'generate_packing_slips'.

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?

Opens with a concrete trigger ('Use this when the user wants a pick list...') and supplies real user phrasings, then names the excluded case ('without packing slips') and routes it to the alternative ('for packing slips use generate_packing_slips'). It also states a negative boundary: it does not check stock levels or change store orders.

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