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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The top-level description itself adds no behavioral detail such as pagination, inactive-record handling, or unsupported OR filters — those live in the criteria parameter description rather than the tool description. This is not contradictory, but it is thin.

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 a single front-loaded sentence naming verb, resource, and system, with no filler. Every word earns its place, and the longer criteria description is justified by the genuinely complex query behavior it documents.

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?

Together with the very detailed criteria schema, the definition gives an agent enough to construct queries, paginate, and avoid unsupported OR or Line-field filters. It falls short of 5 because there is no explicit statement of the return shape and no guidance on when to prefer get_item for a single known record.

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 description coverage is 100%, and the criteria parameter description already documents operators, sort/limit/offset, AND semantics, and QuickBooks limitations. The top-level description adds no parameter meaning, so per the high-coverage baseline this is adequate.

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 clearly names the action (search) and resource (item records) in QuickBooks Online, which immediately distinguishes it from the many create/update/get siblings. It stops short of 5 because it does not explicitly say it returns a list or page, or how it differs from get_item.

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 search_items versus get_item or the other search_* tools, and no mention of when-not-to-use or alternatives. The name implies a search use case, but the description leaves selection among siblings to inference.

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