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

Annotations already cover the safety profile (readOnlyHint, destructiveHint, openWorldHint), but the description adds real value: a documented default filter, semantic definitions of 'open' (released documents with a balance) and 'overdue' (due_before = today), and the auth requirement ('Needs the user's Cotlet API key with access to this app').

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 the defaults and filters. There is mild redundancy ('Open invoices by default' revisited as 'Open invoices are released documents with a balance') and the 'Lists AR invoices from Invoices and Memos' clause restates the opener, but nothing is wasted enough to impede the agent.

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 and five optional parameters, the description covers the returned payload shape, the default scope, filter semantics, and the auth prerequisite. Pagination is handled by the cursor/limit schema fields, so no descriptive gap remains.

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 meaning beyond the schema by defining due_before operationally ('overdue ones are those with due_before set to today') and clarifying the status enum values are the documented filter set.

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 AR invoices from Invoices and Memos') and enumerates the returned fields (customer, dates, amount, balance, status). It also distinguishes itself from the sibling get_invoice by noting that the line detail lives there.

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?

Clearly documents the default scope ('Open invoices by default') and the filter axes (status, customer, due date), and routes the agent to get_invoice for line detail. It stops short of an explicit when-to-use-this-vs-get_invoice statement, but the routing hint is strong.

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