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 known. The description adds valuable behavioral details: how rows are structured (type, depth, values), the meaning of 'id' and its alignment on detail vs summary reports, the omission of all-zero rows (counted in hidden_zero_rows), the 'filters' field reflecting applied parameters, and 'no_data' flag. This goes beyond annotations and clarifies output behavior.

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 sentence but packs in essential details about the return format and behavioral quirks. It is front-loaded with the purpose, then explains the output structure. While it could be broken into shorter sentences for readability, it contains no fluff and each clause adds 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?

Given the tool's complexity (many parameters, a detailed report) and the absence of an output schema, the description explains the return structure thoroughly: columns, column_types, rows with type/depth/values, id alignment, hidden_zero_rows, filters, and no_data. This is sufficient for an agent to understand what the tool returns. Minor gaps exist (e.g., does not describe what the report contains beyond 'balance detail'), but the core context is covered.

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?

The schema description coverage is 100%, meaning all parameters (report_date, date_macro, aging_method, customer, columns, etc.) are already documented in the input schema. The description does not add any parameter-specific semantics beyond what the schema provides. Since the schema carries the full burden, a baseline of 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 clearly states the tool's purpose: 'Generate the QuickBooks customer balance detail report.' This is a specific verb (generate) and resource (customer balance detail report), distinguishing it from summary reports like get_customer_balance by the word 'detail.' The purpose is unambiguous and matches the tool name.

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 does not explicitly state when to use this tool versus alternatives. It focuses on the output structure and behavior but provides no guidance on when to choose this over get_customer_balance, get_aged_receivable_detail, or other report tools. Usage is implied by the name and the fact it generates a specific report, but there is no explicit context or exclusions.

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