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

The description adds valuable behavioral context beyond the annotations: it mentions that totals are recomputed automatically and that the operation is blocked once the invoice is paid or void. Since annotations are all false and don't provide this level of detail, the description enriches the agent's understanding of the tool's side effects and constraints.

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 description is extremely concise: two sentences that convey the essential purpose, behavior, and a key restriction. It is front-loaded with the core action and avoids any unnecessary words or repetition of schema details.

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 relatively simple tool with an output schema, the description covers the main points: what it does, when it's allowed, and a key automatic behavior. It doesn't explain the response format, but that's covered by the output schema. It could mention error scenarios beyond the paid/void block, but overall it is complete enough 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?

The input schema has low description coverage (only quantity has a default note). The description adds some meaning by labeling the line item as 'billable' and mentioning unit_price implicitly, but it does not explicitly explain the purpose of each parameter. It confirms that invoice_id is required, which helps, but the semantics of description, unit_price, and quantity are left mostly to the schema's names and types.

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 clearly states the tool's function: adding a billable line item to a draft or sent invoice. It distinguishes this from sibling tools like create_invoice and update_invoice by specifying the specific action (add line item) and the target resource (existing invoice). The scope is further clarified with 'draft or sent invoice'.

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 implies when to use this tool: when you need to add a line item to an existing invoice, as opposed to creating or updating the invoice itself. It does not explicitly name alternative tools, but the context is clear from the sibling list. It also provides a clear exclusion ('Blocked once paid/void'), which helps agents understand when not to use it.

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