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

The description adds meaningful behavior beyond the annotations: PATCH semantics ('omitted fields remain unchanged'), null-clearing for companyName and currency, and the return of the complete canonical settings. Annotations already indicate destructive and idempotent behavior, so the description need not repeat them. No contradiction with annotations.

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?

Three dense sentences with no filler. The action and scope are front-loaded, and the null-clearing and return behavior are stated efficiently. Every sentence earns its place.

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?

The description covers the core mutation semantics, null behavior, and return value, and the output schema handles return structure details. It does not clarify the semantics of less obvious properties like paymentInfo or senderInfo, but the schema plus self-explanatory names make the definition still work well. Overall, it is complete enough for an agent to invoke 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?

With schema description coverage at only 13%, the description carries extra weight for parameter meaning. It usefully explains null-clearing for two parameters and the general omit-to-keep behavior, but it does not explain senderInfo, paymentInfo, invoicePrefix, defaultDueDate, or invoiceNumberFormat beyond their names. The idempotencyKey description in the schema partially compensates.

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 names a specific verb and resource: 'partially update saved invoice defaults for the connected workspace.' It clearly distinguishes this from sibling tools like update_invoice and update_client by scoping it to workspace-level defaults. The terminology is precise enough that an agent can confidently select it.

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 clearly signals when to use the tool: when modifying saved invoice defaults at the workspace level. It does not explicitly name alternatives such as get_settings or update_invoice, but the resource scope is unambiguous enough to route selection. It lacks explicit exclusions, so it stops short of a 5.

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