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

With no annotations provided, the description carries the full burden of behavioral disclosure. It goes beyond stating a filter to reveal a non-obvious response quirk: the outstanding total is PER CURRENCY, not a single merged number, and explains why this is so ('a single converted number across several currencies corresponds to nothing real'). This is exactly the kind of transparency an agent needs.

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?

Two sentences, front-loaded with the core action. The first sentence states the purpose, the second packs the most important parameter guidance and the critical response caveat. Every phrase earns its place; zero filler.

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 simple list tool with two optional filters and no output schema, the description covers the one genuinely tricky aspect (per-currency totals) and the primary usage case. It does not mention pagination, default status behavior, or how results are ordered, but these are minor given the tool's simplicity and the lack of an output schema. Slightly more would push it to 5.

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?

The input schema already documents both parameters (status with enum-like values, outstanding as boolean) at 100% coverage, so the baseline is 3. The description adds value by explaining what 'outstanding' actually means semantically ('money still owed') and how it affects the response's currency breakdown. This goes beyond the schema's terse definition.

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?

The description opens with 'List invoices' – a specific verb and resource. It then ties the primary filter (outstanding=true) to its exact meaning ('money still owed — issued invoices not yet fully paid'), giving agents a precise mental model. This clearly distinguishes it from invoice-specific tools like invoices_get or invoices_create_draft.

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?

It explicitly instructs when to set outstanding=true and calls it 'the usual question', which is practical, context-rich guidance. However, it does not mention alternatives such as invoices_get for a single invoice or how to combine status with outstanding, nor does it say when not to use this tool. Still, the main usage decision is well covered.

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