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

The single destructiveHint annotation says nothing about side effects, and the description fills that gap richly: not approved, not booked, not numbered into the ledger, not sent, no payment created, and explicitly non-idempotent ('a repeat call creates a second draft'). It also names the endpoint and that Billy assigns the invoice number.

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 a 'WRITE:' marker, then tight declarative sentences — state, what does not happen, idempotency, endpoint. No filler and no redundancy.

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 covers what the operation does and its lifecycle well, but it never hints at what the caller gets back (e.g., the created invoice id) to feed a later get/approve step. Small but real gap for a create tool.

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 100%, so the parameters are already documented. The description adds only the state=draft mapping and that the contact must pre-exist; it does not extend line, currency, or tax_mode semantics beyond the schema, so the baseline 3 is right.

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 plus the exact resulting state: 'WRITE: create ONE invoice in the DRAFT state for an existing contact.' No sibling tool in the list creates invoices, so the agent can immediately distinguish this from the list/get tools.

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?

Explains the intended context clearly — this produces a draft the user reviews, approves and sends in Billy itself, not a finalized or booked document. It also implies the prerequisite (contact must already exist), though it stops short of naming alternatives or explicit when-not-to-use cases.

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