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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The definition goes well beyond that via the criteria documentation: page limits (1000 records, truncation), AND-only filters with no OR, case-sensitive field values, unavailable data (government IDs, birth dates, card details), and inactive-record exclusion. This is rich behavioral context consistent with the annotations, with no contradiction.

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 efficient sentence with zero wasted words and the core purpose front-loaded. The minimalism is a deliberate trade-off: behavioral detail is delegated to the schema, which is a reasonable structure even if the description alone feels thin.

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 read-only search tool with two well-documented parameters and no output schema, the definition covers criteria shapes, operators, restrictions, pagination, and the company disambiguation rule thoroughly. The main gap is the absence of any description of the returned account record structure, which an agent would have to infer or discover.

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 criteria parameter's prose is exceptionally detailed on accepted shapes, operators, field limitations, and pagination semantics. The description itself adds nothing about parameters, so the baseline 3 applies—the schema carries the load as expected.

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 'Search account records in QuickBooks Online' names a specific verb, resource, and platform, so an agent knows immediately what the tool does. However, it makes no attempt to differentiate from siblings such as get_account, get_account_list, or the other search_* tools, which all share the same basic 'search entity records' framing.

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 description itself gives no guidance on when to use this tool versus alternatives like get_account or get_account_list. The schema's criteria prose implies usage contexts (filtering, pagination with limit/offset, Active filtering), which is helpful, but there is no explicit when/when-not logic or named alternatives.

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