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

Annotations cover the safety profile (readOnly, non-destructive, closed-world), so the bar is lower. The description adds genuinely useful behavioral context beyond them: this is a stateful, stepwise decision tool whose response may be an intermediate question rather than a final answer, which affects how an agent must call it.

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?

One dense sentence that front-loads the purpose, then the mechanism and the return shape. No filler or repetition.

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?

No output schema exists, and the description compensates by explaining what comes back (next question or the outcome plus required invoice wording). For a single-parameter, closed-world check this is nearly complete; only the mapping of question ids to real-world meaning is left entirely to the schema.

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% and the enum of question ids is fully documented there, so the baseline would be 3. The description adds real meaning by clarifying that the answers are yes/no values and that partial answers are acceptable ('answers known so far'), which the schema alone does not state.

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+resource: determining whether the domestic VAT reverse charge for construction services applies to an invoice, and names the method (HMRC's decision steps). This clearly distinguishes it from calculate_vat and check_vat_registration among the siblings.

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 operating pattern: pass the yes/no answers known so far and get back either the next question or the final outcome. That tells an agent how to drive the tool iteratively. It stops short of naming alternative tools or stating when this check is unnecessary.

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