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

Annotations already establish read-only, non-destructive, closed-world behavior, so the description's job is supplementary — and it does add real value by disclosing the data model and the currency unit (øre), which prevents unit-interpretation errors. Pagination behavior is disclosed but page size and the terminal/short-page condition are not.

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?

Two short sentences, front-loaded with what the tool returns, followed by the one operational instruction. No wasted phrasing.

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 two-parameter read-only list tool with no output schema, the definition covers the essentials: data model, units, and pagination handoff. It stops short of describing ordering, default page size, or what an empty/terminal page looks like, which an agent may still need.

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 coverage is only 50%, and the description fills exactly the gap: it explains that 'cursor' is fed from a previously returned 'next_cursor', which the bare schema does not say. connection_id is covered by the schema itself, so nothing further is needed there.

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 names the resource ('invoices from the accounting system') and the scope ('one page'), plus a notable qualifier ('canonical model, amounts in øre'). It does not explicitly contrast itself with siblings like list_proposals, but the resource noun is distinct enough for an agent to pick it out.

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 usage instruction is procedural pagination ('Pass next_cursor back as cursor for the next page'). There is no guidance on when to choose this tool over the sibling list/profit tools, no mention of escaping the loop or what happens at the last page.

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