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

Even with strong annotations (readOnlyHint, idempotentHint, non-destructive), the description adds genuinely useful behavioral detail: the tool reports the exact discrepancy between rounding methods, forbids mixing methods, and throws on malformed lines. These are not inferable from annotations alone and materially affect how an agent should call and interpret the tool.

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 one dense, information-rich sentence with no filler. It front-loads the core action ('Total a multi-line invoice in integer cents') and then packs the essential constraints and behavior into the remainder with efficient use of an em-dash.

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 calculation tool with well-specified parameters and rich annotations, the description covers the main behavior, constraints, and failure mode. The only notable gap is that no output schema exists and the description does not spell out the exact return shape, though 'total ... and report the exact discrepancy' gives a reasonable sense of the result.

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 coverage is 100%, so a baseline of 3 applies, but the description adds meaningful semantic value beyond the schema. It explains that rounding values correspond to per-line and total-based ATO methods, clarifies that totals are in integer cents, and ties GST-free lines into the computation. This helps map the enum values to real-world behavior.

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 ('Total'), a clear resource ('a multi-line invoice'), and a precise output unit ('integer cents'). It also distinguishes the tool from nearby siblings like calculate_gst by framing it around full invoices, GST-free lines, and ATO rounding behavior.

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 clear context: this is for multi-line invoice totals with GST handling and ATO rounding. It does not explicitly name alternatives or list when-not-to-use cases, but the scope is specific enough that an agent can identify the intended use.

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