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

The criteria parameter discloses important behavioral traits beyond the readOnly/destructive annotations: one-call returns at most 1000 records, large pages are truncated, filters are ANDed with no OR support, only top-level fields are filterable, field matching is case-sensitive, inactive records are excluded unless Active is explicitly filtered, and sensitive data is unavailable. This is rich, useful behavioral context.

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 focused sentence containing only necessary information: the operation, the entity, and the platform. It is front-loaded and free of filler. The long criteria schema text is justified by the complexity of the query language and does not bloat the narrative description.

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 search tool with no output schema, the definition conveys most of what an agent needs: platform scope, company selection, filter syntax, operator semantics, pagination behavior, and inactive-record handling. It stops just short of fully complete because it does not describe class-specific searchable fields or the shape of returned class records, but the filtering documentation largely compensates.

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%, so the baseline is 3. The narrative description adds no parameter-level meaning beyond what the schema already provides. The criteria parameter's schema description is excellent, but it lives in the schema, not in the tool description, so the description itself does not augment it.

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 ('Search') and resource ('class records') with the platform scope 'QuickBooks Online', so an agent knows exactly what action and entity are involved. It distinguishes from non-class tools by naming the resource, though it does not explicitly differentiate from siblings like get_class or search_accounts.

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 one-line description gives no guidance on when to use search_classes versus get_class for a single record or versus other search_* tools. The criteria schema provides substantial how-to guidance (pagination, filtering limitations, inactive records), but it does not address alternatives or exclusions, leaving usage selection largely implied by the tool name.

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