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 description goes well beyond that by disclosing subtle behaviors: all-zero rows are omitted and counted in hidden_zero_rows, filters lists only the filters QuickBooks confirmed it applied (ignored parameters are absent), and no_data: true signals an empty period. It also explains the id alignment difference between summary and detail reports. This is rich behavioral context that an agent cannot infer from the schema or annotations.

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 dense paragraph that front-loads the core purpose and return structure before diving into edge-case behaviors. Every sentence carries meaningful information about return format, row semantics, or filter behavior. It is longer than strictly necessary, but the density justifies the length; a slight structural improvement would be splitting the return-format details from the edge-case behaviors.

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 report tool with 100% schema coverage and no output schema, the description is remarkably complete. It explains the return structure, row types, value alignment, id semantics, hidden zero rows, filter confirmation behavior, and the no_data flag. An agent has everything needed to invoke the tool and interpret its response correctly. The only minor gap is not explicitly listing the report's default date range when no date parameters are provided, but the schema's optional params make that a minor omission.

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 schema already documents both parameters (params and company) in detail, including the date_macro enum list and accounting_method options. The description adds context about how filters are reported back (filters lists only confirmed applied filters), which indirectly clarifies parameter behavior, but it doesn't add new meaning to the parameters themselves beyond what the schema provides. Baseline 3 is appropriate.

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 opens with a specific verb and resource: 'Generate the QuickBooks trial balance report.' It then details the exact return shape (columns, column_types, rows, row types, depth, values, id semantics), which distinguishes it from sibling report tools like get_balance_sheet or get_general_ledger. The level of specificity leaves no ambiguity about what this tool produces.

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 clearly implies this is the tool to call when a trial balance report is needed, and the detailed return format helps an agent understand what to expect. However, it does not explicitly state when to prefer this over related financial report siblings (e.g., get_general_ledger, get_balance_sheet) or mention any exclusions. The context is clear but the when-not-to-use guidance is absent.

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