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

Annotations only say this is a non-read, non-destructive, open-world, non-idempotent call. The description adds real behavioral context beyond that: hard caps of 200 uploaded images and 500 total prints, flat shipping rates that differ for 1 versus 2+ prints, the warning not to multiply flat shipping by quantity, that couponCode is validated at quote time, and that consent is required for PhotoPrintAgent processing.

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?

A long single paragraph, but the purpose and the item-construction rules are front-loaded and each clause addresses a distinct failure mode (date grids, precomposition, flat-shipping multiplication). Some density could be reduced with formatting, yet almost every sentence earns its place for a complex nested-array request.

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 nested objects, multiple artwork modes, and an output schema that already documents the return shape, the description is nearly complete for correct invocation. The gaps are the unexplained campaignId, no mention of non-idempotency implications on retries, and no explicit alternative-tool routing.

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 14% schema description coverage, the description carries the burden, and it does so for most of the request: order-level productId defaults to photo-4x6, per-item productId overrides, array order equals print order, quantity counts complete products rather than individual images, and the calendar object is demonstrated with startYear/startMonth. campaignId is never explained, and guestToken's usage only lives 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?

The description opens with a specific verb and resource: quote private uploaded photo IDs plus a US destination, optionally per productId from list_products. That distinguishes it from create_print_order and pay_print_order by scope. It never names the near-siblings estimate_print_price or preview_print_price, so the agent must infer the difference between quoting and estimating.

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?

It gives concrete construction rules for the main cases: items:[{photoId,...}] for a single image, items:[{photoIds:[...]}] for multi-image designs, calendar artwork needing a cover plus one photo per month, and composition artwork needing per-image dimensions with no precomposed files. It also warns never to upload date grids or split sides into separate items. What it lacks is explicit routing against sibling tools like estimate_print_price versus preview_print_price.

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