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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new context: the return payload (named results, units, formula, assumptions, method version, source URL) and explicit negative scope ('no prices or omitted costs are looked up; no private projects or purchases are accessed'). It stops short of stating validation failure behavior or error modes, which matters given the version-mismatch rejection.

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 lead sentence is well front-loaded and does real work. But 'Use this tested BusCalc worksheet when the task matches its inputs and scope' is boilerplate that consumes a sentence without informing, and the closing scope sentence packs three distinct claims into one 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?

With no output schema, the description compensates by enumerating the return fields, and the closed-world/read-only boundary is clearly set, which suits a deterministic single-formula calculator. The remaining gap is the version-mismatch rejection path and the unexplained units parameter.

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 compensate, and it largely does not. The cost and margin semantics live entirely in the schema, and the 'units' object parameter — an empty-properties object the agent might reasonably try to populate — is never explained anywhere in the definition.

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 transformation: 'Convert cost and desired gross margin into price without confusing markup.' The verb (convert), the two inputs, and the output (price) are all named, and the markup-vs-margin distinction separates it from siblings like buscalc_service_business_hourly_rate that also touch pricing.

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?

'Use this tested BusCalc worksheet when the task matches its inputs and scope' is circular — it tells the agent to use it when it applies, without saying what that looks like. No sibling tool is named as an alternative, and there is no explicit when-not condition, even though nine related calculators exist.

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