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

Annotations already establish readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The criteria parameter description adds meaningful behavioral context beyond that: one call returns one page of at most 1000 records, large pages are truncated, filters are AND-only, field values are case-sensitive, and certain data (government identifiers, birth dates, card-processing details) is unavailable. The main description itself is terse, but the definition as a whole discloses the tool's operational traits.

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 main description is a tightly scoped single sentence with no filler. The criteria text is a dense block of necessary operational detail, front-loaded with accepted formats before caveats; it could benefit from structural formatting, but every clause carries functional value.

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 two-parameter, zero-required-parameter read-only search tool with no output schema, the definition covers company selection, criteria construction, pagination, truncation, and data-availability limits. The notable omissions are the response shape and routing to related siblings like get_open_invoices or get_invoice, but neither is required for correct invocation.

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%, but the criteria text goes far beyond the bare union type (object/array/string/null). It specifies the three accepted shapes, operators (=, <, >, <=, >=, LIKE with % wildcards, IN), AND semantics, the whitelist of filterable fields, case-sensitivity, and pagination options (limit, offset, count, asc/desc) — everything needed to construct a valid call. The company parameter's optional-when-single rule is also documented.

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 states a specific verb and resource: 'Search invoice records in QuickBooks Online.' This clearly separates it from resource-level siblings like search_bills or search_customers. However, it does not differentiate from get_invoice or get_open_invoices; the agent must infer that 'search' implies flexible criteria-based lookup.

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?

No explicit when/when-not guidance or alternative tools are named in the description; an agent must infer from the name when to pick this over get_invoice or get_open_invoices. The criteria parameter text offers strong how-to guidance (narrow with filters, walk pages with limit/offset), but that is usage-within-tool, not tool-selection guidance.

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