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

Beyond the annotations (which only declare it is a non-read-only, non-destructive write), the description discloses the required billing write scope, the need for a claimed workspace, and the concrete failure mode — a self-registered sandbox key is refused with 403 until a human claims the workspace. Defaults for currency and status are also stated, which an agent needs in order to predict the resulting record.

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?

The capability and required parameters come first, followed by the sibling distinction and then prerequisites — a sensible order with no filler. The workspace-claim sentence is slightly long but carries non-obvious failure information, so it earns its space.

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 7-parameter mutation with no output schema, the description covers inputs, defaults, required scope, workspace preconditions, and the key sibling boundary. An agent has everything needed to decide to call it and to predict success or a 403.

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 would be 3, but the description adds real meaning: it marks which parameters are optional, states status defaults to draft (not stated in the schema), and confirms the USD currency default. It does not elaborate on formats such as due_date or metadata contents, which the schema already covers.

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 a specific verb+resource ('Add an invoice for a customer') and immediately enumerates the fields it accepts, including which two are required. It also explicitly disambiguates from the most confusable sibling by naming send_invoice and the behavior that separates them.

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 does not email the customer; send_invoice does' gives an explicit alternative and the condition that selects it, and the credential/workspace prerequisites tell the agent when a call will fail. It stops short of covering update_invoice vs create_invoice for existing records, so it is strong but not exhaustive.

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