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

Annotations already establish readOnly/idempotent/non-destructive, and the description still adds real behavioral payload: both return shapes for HUI 0.1 vs 1.0, the meaning of outcome values, the critical clarification that ok:false is still a successful call so the agent can self-correct, and the zero-tolerance rule for interactive blocks. That is exactly the context annotations cannot carry.

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?

Dense and front-loaded: the side-effect-free framing comes first, then return shapes, then the error-tolerance rule. Each sentence carries information, though the HUI 0.1/1.0 jargon arrives without setup and the 'form' vs 'document' terminology shifts mid-description.

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?

With no output schema, the description fully covers both return payloads, the validity outcome enum, the ok:false semantics, and the rejection rule for interactive blocks. For a read-only validator with four optional parameters, an agent has everything needed to call it and interpret the result.

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 is 3, but the description adds the mapping of document format to parameter and to output shape (HUI 0.1 object → {ok, hui, diagnostics, fields}; markdown → {ok, outcome, hui, registry, blocks, diagnostics}), which tells the agent which input form to choose. It says nothing about 'lenient', leaving that entirely to the schema.

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 (check/validate) plus the resource (a form/HUI document) and immediately distinguishes itself from the handoff siblings: 'without creating a handoff and without contacting the person.' An agent can tell this apart from send_ui_handoff or delegate_handoff without opening any schema.

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 opening clause implicitly defines the when-to-use case (validate with no side effects, as opposed to sending a handoff), and the 'labs' note explicitly routes that parameter's real use to list_blocks. It stops short of naming a specific alternative tool for the send-vs-check decision, so it's clear context rather than a full when/when-not matrix.

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