list_expenses

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

Annotations already establish read-only, idempotent, open-world, and non-destructive behavior. The description adds useful operational details beyond that: it is scoped to the current page, filters and booked-expense details are not validated, and currency display text is retained.

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 description is short, front-loaded with the verb and resource, and separates the caveats into a second paragraph. However, 'Current page only; check complete' is cryptic and reduces the clarity that the concise structure otherwise provides.

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 simple read tool with one optional parameter, an output schema, and strong annotations, the core purpose and caveats are present. The main gaps are the implicit drafts parameter mapping and the ambiguous 'check complete' phrase, making the description adequate but not fully self-sufficient.

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?

The only parameter, drafts, has no schema description and the description never explicitly maps it to the 'expense-draft view' or states what true/false does. It hints at two views but leaves the agent to infer how the boolean selects between them.

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 uses a clear verb ('Read') and identifies the resource ('saved booked-expense or expense-draft view'). It distinguishes this expense-focused tool from siblings like list_invoices and list_declarations, though the phrase 'Current page only; check complete' is ambiguous.

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?

There is no explicit guidance about when to use this tool versus its siblings. 'Current page only' and the caveats describe limitations, not selection criteria, so an agent cannot tell when to prefer list_expenses over related list tools.

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