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

Even though annotations exist, the description adds substantial behavioral detail beyond them: changes_requested is non-terminal, maxIterations defaults to 5 and can fail with max_iterations_exceeded, webhooks fire on every transition, and interactive pages MUST expose window.__VR_HITL_GET_SETTINGS__. It also explains timeout semantics and option classification. 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?

The description is a single dense paragraph that front-loads the core behavior and then efficiently covers defaults, edge cases, and integration guidance. Every sentence carries useful information, though it could be slightly better organized with breaks between the core flow, integration details, and the HTML requirement.

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?

Despite having no output schema and 9 parameters, the description covers the critical behavioral paths, defaults, failure modes, webhook integration, and the HTML global requirement. It references PARTNER-WEBHOOKS.md for payloads, but leaves the return shape of poll/continue flows to inference and does not elaborate on sessionToken or contextUrl semantics. Overall, it is strong but not exhaustive for a tool this complex.

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 67% and the description meaningfully augments key parameters: webhookUrl is explained with transition examples and a preference rule, maxIterations gets default and failure semantics, options get default values and classification behavior, and agentOutput gets a semantic explanation. A few parameters like tenantId, sessionToken, and contextUrl remain underexplained, so it doesn't reach a 5.

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 precise verb and resource: "Create a human-in-the-loop review on the live artifact." It immediately distinguishes this from sibling tools by referencing continue_decision for the changes_requested path and explicitly preferring this over poll_decision for automation. This is a clear, specific, and sibling-aware purpose statement.

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 gives direct when-to-use guidance: use it for human review on the live artifact, prefer webhookUrl over poll_decision for automation, and call continue_decision after regenerating when changes are requested. It also explains the default review flow and the non-terminal nature of Request changes, providing clear context versus alternatives.

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