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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds real domain behavior: which fields are excluded (invoice_number, po_number) and that amounts are bare numbers with no embedded currency. Missing only return-shape/pagination details, which is minor for a single-record get.

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 tight sentences, front-loaded with the primary operation before the exclusion, the sibling alternative, and the currency caveat. No filler; each clause carries information the agent needs.

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 returned fields and flagging both the excluded fields and the missing-currency pitfall, plus sibling routing. An agent has everything required to call and correctly interpret this 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?

Only one parameter (id) and schema coverage is 100%, so the schema already documents it fully. The description adds no syntax beyond 'by ID', and the enumerated fields describe the response rather than the input, so this sits at the baseline.

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?

Specific verb (Get) plus resource (project-scoped expense) and scope, with an explicit list of what the record contains (amount, date, receipt, linked project/work order). It clearly distinguishes itself from the similarly named asset_cost record type that shares the 'Expense' label.

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?

States when-not-to-use this tool and names the alternative: invoice_number/po_number live on asset_costs, so use get_asset_cost for that record type. It also directs the agent to call get_organization_settings for currency_code before quoting an amount — actionable routing on both edges.

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