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

Annotations already establish read-only, idempotent, non-destructive and closed-world behavior, so the bar is lower. The description nevertheless adds real value: it lists what is returned (named results, units, formula, assumptions, method version, source-page URL) and explicitly states that no prices or omitted costs are looked up and no private projects or purchases are accessed, reinforcing the closed-world hint with concrete scope.

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 formula is front-loaded in the first sentence and the returns/scope sentence is substantive. The middle sentence ('Use this tested BusCalc worksheet when the task matches its inputs and scope') is filler that could be cut or replaced with actual guidance.

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?

The description covers the computation, the return payload, and the no-lookup scope, which is reasonable for a read-only calculator with no output schema. However, for a nested-input tool with only 33% schema coverage it does not explain how to handle the reportingPeriod alignment or mixed-period costs beyond a passing mention, and it offers no routing against the similar per-hour sibling.

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 33%, so the description must carry some load, and it does clarify that costs and distance must be measured for the same period (reinforcing the reportingPeriod semantics). It adds nothing about units or modelVersion beyond what the nested schema descriptions already say. Partial compensation, so the baseline 3 applies.

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 first sentence states a concrete verb chain and resource: sum vehicle operating, ownership and driver costs, then divide by productive miles. That makes the computed metric unambiguous. It does not, however, point at the closest sibling (buscalc_equipment_ownership_cost_per_hour) to say how the per-mile metric differs from the per-hour one, so differentiation is left implicit.

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?

Usage guidance is limited to the circular instruction 'use this tested BusCalc worksheet when the task matches its inputs and scope,' which gives no decision criteria. The one real boundary is the warning not to mistake this for cost per all odometer miles, which does help scope the metric. No alternative tool or when-not condition is named.

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