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

With readOnlyHint already declaring this a safe read, the description earns credit for adding real behavioral facts: newest-first ordering, the underlying endpoint (GET /credit_notes), and the fact that the response becomes { data, pagination } when more pages exist.

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 compact sentences, ordering stated up front, no filler. Every clause carries information an agent can use.

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 six-parameter listing tool with full schema coverage, the description supplies the missing pieces: ordering, response envelope, and pagination behavior (there is no output schema, so the envelope note is important). It stops short of explaining pagination strategy end-to-end, but the schema covers the cursor mechanics.

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%, including notable details like the comma-separated date format and the cursor semantics of created_before, so the baseline 3 applies. The description repeats no parameter semantics and adds nothing beyond the schema here.

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 gives a specific verb and resource ('List credit notes'), clarifies the domain term with '(refund documents)', and states ordering ('newest first'). The list vs get distinction from quaderno_get_credit_note is implicit in the name and verb rather than explicitly stated.

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 spelled out: it's a read-listing tool with newest-first ordering, but there is no explicit when-to-use, when-not-to-use, or routing to alternatives such as quaderno_get_credit_note or the generic quaderno_request.

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