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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds real value beyond that: it specifies that an empty History array means "no recorded changes" whereas success=false or a missing History is a failed lookup — a distinction an agent would otherwise misread as "no history." It also discloses the resolution path (resolve Product ID via Listing/GetListings, then matching variation). Minor redundancy with the existing output schema.

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?

Well structured with labeled sections (Purpose, Use when, Input, Output, Search terms) and the key scope statement front-loaded. Slightly padded by the meta-openers ("Dedicated HGRApi tool for GET api/...", "it is not a generic endpoint caller"), which repeat information no agent needs to select the tool.

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?

The output-schema burden is offloaded and the failure-versus-empty reporting contract is well covered. But the description's Input section describes a parameter set that does not match the one-property schema, so an agent following the description could try to supply a variation id that the tool rejects (additionalProperties: false). That mismatch undercuts completeness for a tool whose whole job is a single-key lookup.

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 single parameter is channelOAuthId, but the description's "Input:" block documents a required variation id ("positive internal ListingVariationId, not the parent ListingId, supplier ProductSourceId or marketplace Product ID") that does not exist in the schema. It then says channelOAuthId is "resolved internally," which contradicts the schema marking it required and pointing to hgr_list_channels. This leaves the agent unsure which id to actually pass.

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 with unusual precision: "Reads the recorded stock quantity change history shown in HGRWeb for one listing variation," plus an explicit endpoint binding. However, it never differentiates itself from the near-identical sibling hgr_get_listing_stock_history (or hgr_get_searchproduct_pricechanges for price history), which an agent could easily confuse with this tool.

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?

Provides a genuine "Use when" clause enumerating concrete triggers (stock history, stock changes, quantity changes, inventory history, availability timeline) and an explicit exclusion ("Current stock in the product details is not its history"). What it lacks is forward routing to an alternative — no mention of when to prefer its stock-history siblings, so the agent must infer the boundary node selection.

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