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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds meaningful context beyond that: default page size 50 and max 200, the requirement for a Cotlet API key with access to the app, and that totals are in cents with currency and each invoice has exactly one state.

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 core action and return shape in the first sentences, then layers pagination, filtering, and auth. Mostly efficient, though "Each invoice has exactly one state" is slightly redundant padding between the filter and totals sentences.

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?

With no output schema, the description carries the return-value burden and does so by enumerating the invoice fields, currency units, and the invoice_number identifier. Combined with pagination and auth notes, an agent has enough to call it correctly, though cursor-based pagination mechanics are only briefly implied.

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 all three parameters are already documented in the schema. The description restates the state enum values and the per-page semantics (50 default, up to 200) but adds no syntax or format detail beyond the schema, making the baseline 3 appropriate.

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 clear verb and resource ("Lists invoices") and enriches it with the fields returned (number, account, state, totals, dates). It is distinguishable from Recurly's get_invoice and refund_invoice, which it references, but does not explicitly contrast against other Recurly list tools, keeping it at 4 rather than 5.

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 context is implied: it tells you filterable states and that the returned invoice_number feeds get_invoice/refund_invoice, which hints at follow-on calls. However, it never states when to use this list tool versus get_invoice or list_transactions, and offers no when-not guidance.

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