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

With all annotations at false/default values, the description carries the behavioral burden and delivers: it discloses the return shape ('saved id with the rate used, where that rate came from and the money'), the currency behavior ('in the rate's own currency'), and the exclusivity constraint. It does not contradict the annotations — a record-creating write aligns with readOnlyHint=false.

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?

Three short sentences, each earning its place: the purpose, the critical exclusivity constraint, and the return-value contract. The most important information is front-loaded in the first sentence, with zero filler or repetition of schema boilerplate.

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?

There is no output schema, so the description's return-value disclosure (id, rate, rate source, currency) fills a real gap. The schema covers all parameter semantics, defaults, and the tax caveat, so together the package is complete for a 9-parameter tool. Minor omission: the description doesn't note that missing 'project' hides the claim from expense_summary/expense_to_invoice, though the schema's project field does.

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 every one of the 9 parameters is individually documented in the schema, which establishes the baseline of 3. The description adds the high-level pricing context and the km/miles exclusivity, but that constraint is already repeated in both parameter descriptions, so the description contributes no additional parameter-level meaning.

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 opens with a specific verb and resource ('Record a business trip as an expense') and adds the pricing mechanism ('priced as distance x rate'), which clearly distinguishes it from the sibling expense_add for general expenses. The mutual-exclusivity constraint ('Give exactly one of km or miles') further sharpens the scope.

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 is implied rather than stated: the 'business trip' framing suggests this tool is for mileage claims versus expense_add for other expenses, but the description never names an alternative or gives an explicit when-to-use/when-not-to-use rule. The useful exclusion ('NOT a tax calculation') lives in the schema's region parameter, not in the description.

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