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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description's one genuinely additive behavior note is that the Header channel / ChannelOAuthId is resolved internally, so the agent need not supply it. It adds nothing about what the call returns or any rate/size constraints on image retrieval.

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?

The route is front-loaded and that is the useful part, but the body is templated filler: 'This is an explicit tool with a fixed endpoint; it is not a generic endpoint caller', 'Search terms: sales getorderimage orderid cache', and 'Output: Returns the result or applies the effect' consume space without informing. The restated purpose and use-when sentences duplicate each other.

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?

An output schema exists and annotations are rich, so return format and safety need not be explained. What remains unexplained is the core semantic question — what 'cache' controls and what the image response represents — leaving the agent unable to reason about the call beyond its URL shape.

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 3 would be the baseline, but the description actively muddies things: it declares orderId as int while the schema types it as string. Worse, the 'cache' parameter — the only non-obvious one — is never explained anywhere; the agent cannot tell whether it is a cache key, a boolean-like flag, or a path segment.

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 does name the concrete HTTP resource (GET api/Sales/GetOrderImage/{orderId}/{cache}) and usefully clarifies that this is a fixed-endpoint tool rather than a generic caller. But the actual purpose statement — 'Provides the GET get order image operation in sales/order operations' — is a restatement of the name, and it never says what an 'order image' is (photo/scan of the order? rendered document?) or why a client would want it.

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?

The 'Use when: Use it when a client needs to run the get order image operation' clause is circular and gives no decision criteria. No alternative sibling is named (not even hgr_get_sales or the sales order-loading tools), and there is no when-not guidance.

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