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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, and the description reinforces the read-only nature. It adds context about Shopify fraud-risk filtering and a recent window, but the statement 'medium or high fraud risk' is not fully accurate because min_level can be set to LOW. It does not describe output details, though an output schema exists.

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 description is short and front-loads the core domain in the first sentence. The second sentence, 'Read-only.', is redundant with the readOnlyHint annotation, so not every sentence earns its place. Still, there is no filler or irrelevant detail, and the structure is clean.

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 2-parameter tool with fully documented schemas and an output schema, the description is mostly sufficient but minimal. It omits any when-to-use guidance and its threshold wording is slightly misleading given the LOW option. Given roughly 60 siblings, an explicit use-case or alternative statement would improve completeness.

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?

The input schema has 100% coverage with detailed descriptions of both parameters, including defaults, ranges, and enum meanings, so the baseline is 3. The description adds no parameter-level detail: 'recent window' is vaguer than the days parameter, and 'medium or high' is less precise than the min_level enum.

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 names a concrete resource ('Shopify-flagged orders') and a specific filter ('medium or high fraud risk'), with a temporal scope ('recent window'). It lacks an explicit verb like 'returns' or 'generates', but the tool name and resource make the primary action clear. It does not explicitly distinguish itself from sibling order-related tools, though the fraud-risk angle provides some differentiation.

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?

There is no guidance on when to use this tool versus alternatives such as lookup_order, search_orders, or other run_* audit tools. The description does not mention exclusions or recommend this over sibling tools. The use case must be inferred entirely from the resource description.

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