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

Annotations already cover read-only/idempotent/non-destructive, but the description adds real semantics the annotations cannot: an empty History array means 'no recorded changes' while success=false or a missing History is a failed lookup, not evidence of no history. It also notes the channel/ChannelOAuthId header is resolved internally, which affects whether the agent must supply it.

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 front-loaded with labeled Purpose/Use when/Input/Output sections, but the opening two sentences ('Dedicated HGRApi tool for GET...', 'not a generic endpoint caller') are boilerplate that add no decision value, and some content duplicates the output schema.

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?

Covers what the tool returns, how to resolve the variation id via Listing/GetListings, how to handle multiple matching variations, and how to interpret empty versus failed results. The one hole is the absent 'id' parameter vs the schema's channelOAuthId, which leaves the actual call shape slightly ambiguous.

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% for the single channelOAuthId parameter, so the schema already carries the baseline. The description instead spends its input section on a required 'id' (ListingVariationId) that does not appear in the input schema at all, which is informative about disambiguation but creates a mismatch an agent must reconcile.

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 ('Reads the recorded selling price change history ... for one listing variation') and scopes it to exact_variation, so the intent is unambiguous. It does not differentiate from the near-identical sibling hgr_get_listing_price_history, which is the main gap at this level.

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' clause enumerates trigger phrasing (price history, price changes, previous selling prices, price timeline) and excludes a tempting alternative ('Current price in the product details is not its history'). It stops short of naming the overlapping sibling tool as an alternative to prefer in any case.

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