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

Annotations already declare readOnly/idempotent/non-destructive, yet the description adds substantial operational detail: per-supplier caching and refresh rules (AliExpress, ASOS UK, Matalan, Home Bargains), preservation of explicitly selected SKUs and variation labels, error behavior (ErrorType=UnknownProduct vs. OtherUrls for non-product pages), and Debug payloads for admin/impersonated sessions. This is exactly the beyond-annotation context the dimension rewards.

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?

Purpose is front-loaded and the Purpose/Use when/Input/Output skeleton is scannable, but the body sprawls into supplier-by-supplier edge-case prose (ASOS size identity, AliExpress duplicate-size handling) that is unlikely to change how the agent invokes a two-parameter call. Filler like 'Search terms: listingcreate getdata' and 'This is an explicit tool with a fixed endpoint; it is not a generic endpoint caller' does not earn its place.

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 POST with an output schema already documenting return shape, the description still covers input composition, refresh semantics, partial-success and error paths, and privacy scoping of Debug data. An agent has everything needed to call it correctly and to interpret ambiguous results.

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 100% schema coverage the baseline is 3, but the description goes further by unpacking the otherwise opaque 'body' parameter into Url plus optional ExtraData with selected variation labels and native skuId, and by confirming channelOAuthId is the current ChannelOAuthId header resolved internally. It stops short of naming field-level constraints or error cases for malformed bodies.

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 states a specific verb and outcome — 'Resolves one supplier URL into validated product and draft-listing data for the extension's manual product flow' — plus the exact endpoint (POST api/ListingCreate/GetData). It does not, however, differentiate itself from the near-identical sibling hgr_post_listingcreate_getdatabypsids or hgr_post_listingcreate_editpending, leaving the agent to infer which one applies.

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?

Explicit 'Use when: Use when the extension submits one supplier URL and needs the product details required to prepare a manual product' gives a clear triggering condition. It also names a boundary ('Category filling is diagnosed separately through ChannelListing/GetCategorySpecifics; browser-side changes are not observed here'), but never routes the agent away from the psid-based sibling, so alternatives are only partially covered.

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