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

Annotations already declare the call read-only and non-destructive, but the description adds substantial behavioral nuance: hidden_zero_rows accounting, filters echoing only parameters QuickBooks actually applied, and no_data signaling an empty period. It also documents row type/depth/value semantics and how id relates to label cells. This goes well beyond what the annotations alone provide.

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 purpose is front-loaded and no sentence is padding. The return-format sentence is dense and somewhat run-on, but given the lack of an output schema, every clause earns its place. It could be better structured, but it is not bloated.

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?

With no output schema and nested return objects, the description covers the essential contract: top-level keys, row types, depth, value alignment, id meaning, hidden-zero handling, filter echo, and empty-period behavior. This is sufficient for an agent to invoke the tool and correctly interpret its results. The only notable gap is usage positioning, which is already accounted for in the usage_guidelines dimension.

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 input schema already documents all parameters thoroughly, including date formats, date_macro choices, and enums for accounting_method, summarize_column_by, and arpaid. The description adds little about how to set parameters; its filter-echo note is about output behavior rather than parameter syntax. With 100% schema coverage, the baseline score 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?

Opens with a specific verb and resource: 'Generate the QuickBooks customer balance report.' This clearly distinguishes it from create/update/delete siblings and from unrelated report tools like get_cash_flow or get_profit_and_loss. However, it never explicitly positions itself against the closely related get_customer_balance_detail, so some sibling differentiation is left to inference.

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 gives no guidance on when to choose this tool over alternatives. It names no siblings such as get_customer_balance_detail, get_customer_sales, or get_customer_income, and it states no exclusions or when-not-to-use conditions. An agent must infer selection entirely from the tool name and nearby context signals.

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