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

With all annotation flags false, the description takes on the full burden of explaining behavior. It discloses that updates are partial and that the operation is blocked in paid/void states, adding context beyond the annotations. This is exactly the kind of behavioral guidance an agent needs to anticipate failures.

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?

Four short sentences deliver the main action, update semantics, state restrictions, and required parameter with zero fluff. The critical scope and constraints are front-loaded.

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 mutation tool with 8 parameters, no output schema, and false annotation flags, the description is remarkably complete: it states the state scope, partial-update behavior, blocked states, and required identifier. Nothing essential is missing for an agent to invoke 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 description coverage is only 25%, so the description must compensate. It lists the updatable categories (client, terms, due date, tax rate, notes) mapping to most parameters and restates that invoice_id is required. It doesn't detail every parameter (e.g., currency), but it covers enough to bridge the schema gap.

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 uses a specific verb ('Update'), names the resource ('draft or sent invoice') and enumerates the affected fields ('header fields (client, terms, due date, tax rate, notes)'). It clearly distinguishes itself from siblings like add_invoice_line_item, void_invoice, and send_invoice through this explicit scope.

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 explicitly states when to use the tool (draft or sent invoices) and provides a clear when-not condition ('Blocked once paid/void') with an explicit alternative ('void and re-issue instead'). It also communicates the partial-update usage pattern with 'Only the fields you pass change.'

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