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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description still adds real value by declaring the return payload — named results, units, formula, assumptions, method version and a source-page URL — and by stating that no prices are looked up and omitted costs are not inferred, which sets expectations about assumptions baked into the result. It does not mention error behavior on version mismatch, but overall it goes meaningfully beyond the annotations.

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?

Four short sentences, front-loaded with the computation, then the usage caveat, then the return shape, then the scope exclusions. No restatement of the title and no filler beyond the arguably weak "matches its inputs and scope" clause.

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 tool with no output schema, the description supplies a solid account of what comes back (named results, units, formula, assumptions, method version, source URL), which is the main completeness risk. The gap is the conditional input model, which the description never explains despite the nested object and if/then branching. Otherwise adequate for a three-parameter worksheet tool.

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 only 33%, and the description never explains the key input decision: recipeEntry selects between supplying an ingredient list versus a known batch cost, with different required fields in each branch. It also never clarifies the portions denominator or the units object. The phrase "package prices and quantities used" gestures at the ingredients path but leaves the conditional input structure entirely to 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?

States a specific verb and resource — ingredient cost of a batch and cost per sellable portion — derived from package prices and quantities used. That computation is distinct from every sibling (break-even, loan payment, fleet cost per mile), so an agent can identify it without opening the schema. It stops short of explicitly contrasting with alternatives, which keeps it out of the top band.

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 only routing guidance is "Use this tested BusCalc worksheet when the task matches its inputs and scope," which is close to circular and names no alternatives. The negative scope clause (no prices or omitted costs looked up, no private projects or purchases accessed) does usefully tell the agent this is not a data-retrieval tool, which lifts it above no guidance at all. An agent still has to infer when to prefer this over sibling cost tools.

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