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

The annotations already state that this is a read-only, idempotent, closed-world, non-destructive computation. The description usefully adds that tiers, accelerators, quota percentages and caps are applied, that results are computed in cents, and that it won't judge fairness. However, it claims "Does not handle draws", but the schema exposes draw_amount and draw_type on both plans, so it contradicts the structured data and could mislead an agent about whether draws are respected.

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?

One long but well-structured sentence with the trigger, the computed outputs and the scope limits, followed by two short exclusion sentences; it is reasonably front-loaded. A small amount of density could be trimmed, and the incorrect draws clause is wasted text, but overall there is little padding.

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 complex nested-schema tool, the description covers the purpose, the outputs and routing, and an output schema exists so return values need not be explained. But the "does not handle draws" statement conflicts with the plan schema and leaves the agent unsure whether draw parameters matter, which is a completeness gap on a non-trivial input field.

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 both the plan objects and the sales_levels/currency parameters are already well documented (defaults, examples and formats included). The description only alludes to "several sales levels" and adds no syntax or default information beyond the schema, so the 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 gives a specific verb and resource (compare two commission/comp plans) and states exactly what the output contains: payouts at several sales levels, the difference, and the crossover point. It distinguishes itself from the sibling calculate_commission by scoping itself to two plans, so an agent can separate the two without opening the schema.

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?

It includes concrete trigger phrases ("compare these two comp plans", "which plan pays more at 120% of quota"), an explicit exclusion ("Do not use for a single plan's payout"), and names the alternative (calculate_commission). This is the when-to-use / when-not-to-use / alternative pattern done properly.

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