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

Annotations cover the safety profile (readOnly, non-destructive), and the description adds genuinely new behavioral facts: newest-first ordering, default exclusion of invalidated invoices, a 200-invoice page cap, the next_cursor-to-cursor pagination handoff, and the Cotlet API key/access requirement.

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?

Front-loads the resource and returned fields, then layers filters, pagination, and auth in short declarative sentences. Slightly dense with the inline status enum repeated from the schema, but no sentence is wasted.

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?

No output schema exists, so the description carries the return-shape burden and does so by naming the fields returned. Combined with pagination, default filtering, and auth requirements for a zero-required-parameter list tool, an agent has everything needed to call it correctly.

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, but the description adds real meaning: it explains that invalidated is opt-in only, that date filters bracket invoice date, and that the returned next_cursor should be passed back as cursor — semantics the schema field descriptions only sketch.

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 and resource ('Lists sales invoices') plus the fields returned (customer, number, dates, totals, status) and the default ordering (newest first). It implicitly distinguishes itself from get/approve/send siblings, but never names the closest sibling, list_unpaid_sales_invoices, so the boundary between the two is left to the reader.

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 clear filtering context (status, customer, date range) and a useful conditional rule: invalidated invoices appear only when that status is explicitly requested. It stops short of naming alternatives — e.g. that unpaid-only listings belong to list_unpaid_sales_invoices — so when-not-to-use is missing.

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