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

Annotations already establish readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds real behavioral value beyond that: exact boolean logic for 'overdue' (due_date<today AND balance_due>0 AND not paid/cancelled/refunded) versus 'outstanding', plus the returned field list. It does not mention pagination behavior or row caps beyond what the schema states.

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-loaded with the purpose, then filter semantics, then return shape. Dense and information-bearing with no filler, though the parenthetical logic and return-field enumeration make it somewhat long for a three-parameter tool.

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 no annotations covering return data, the description usefully enumerates what is returned (id, invoice_number, totals, balance_due, due_date, status, customer name). Combined with the filter definitions, an agent has enough to call it correctly; only pagination/ordering is unaddressed.

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 meaningfully enriches the enum beyond the schema's terse 'Invoice state filter.' by spelling out the business logic behind overdue vs outstanding vs paid, which is not derivable from the schema.

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+resource ('Find invoices') and immediately characterizes scope through the filter modes, which distinguishes it from aggregation siblings like ar_aging or get_ar_aging. It does not explicitly name an alternative tool, so it stops short of a 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?

The description defines each filter value precisely, which implies how to select the right mode, but it never states when to reach for this tool over siblings such as ar_aging, quotes_to_follow_up, or unbilled_completed_jobs. Usage context is implied rather than explicit.

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