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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=true, so safety is covered. The description adds two behavioral facts beyond the annotations: results are ordered newest-first and the two id filters are mutually exclusive. Pagination behavior is left to the schema rather than described, a minor gap.

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?

A single front-loaded sentence: what it lists, in what order, and the filter rule. The trailing route list is compact and adds API mapping value. No filler or redundancy.

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 read-only list tool with full schema coverage and annotations, the description supplies the filter rule and ordering. Since no output schema exists, it does not describe the returned note shape, but that is the only material omission for a tool of this complexity.

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 100%, so the baseline is 3. The description beats that baseline by stating the mutual-exclusivity constraint between invoice_id and customer_id, which the schema property descriptions ('Only this invoice's notes') do not convey. Nothing is added for page/per_page.

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?

States a specific verb (List) and resource (collection notes) plus the scoping modes: one customer, one invoice, or all. Sort order ('newest first') is included, and the sibling invoiced_add_note is clearly a different operation (write vs. list). An agent can distinguish it from every other list_* sibling by the resource.

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?

Gives an explicit selection rule: supply exactly one of customer_id/invoice_id, or neither to get everything. That is strong routing guidance. It stops short of naming alternative tools (e.g., for a single note) or stating when this tool is the wrong choice, so it doesn't reach 5.

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