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

Annotations only provide readOnlyHint=true and destructiveHint=false; the description goes far beyond by documenting row types, depth, Money-as-number values, id alignment on summary vs detail reports, hidden_zero_rows, the filters echo with ignored params omitted, and the no_data flag. This gives an agent an accurate model of the tool's 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?

Every sentence carries a distinct fact about the return shape or edge-case behavior, with the core purpose front-loaded. The description is dense but not bloated, and the structured enumeration of return fields reads efficiently.

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?

There is no output schema, yet the description manually documents columns, column_types, rows, row type and depth, id alignment, hidden_zero_rows, filters, and no_data. Combined with the self-describing input schema and safety annotations, an agent has enough to call and interpret the tool correctly.

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?

With 100% schema coverage, the schema already documents params and company. The description adds valuable semantic context: ignored filter parameters silently disappear from the returned filters list, and no_data explains a period with nothing to report. It doesn't restate syntax, but it clarifies interpretation beyond the schema.

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 department sales report'), and the detailed return-shape explanation makes it unmistakable from sibling tools like get_class_sales or get_customer_sales. Even without naming alternatives, it fully identifies what the 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 report name implies when to use it for department-level sales reporting, but there is no explicit statement of when to prefer it over sibling sales-report tools or what inputs select it. It provides clear context, but not exclusions or alternatives.

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