Skip to main content
Glama

Invoke Human Tool

Check a form

validate_ui
Read-onlyIdempotent

Check a form without creating a handoff and without contacting the person. A HUI 0.1 document returns { ok, hui, diagnostics, fields }. HUI 1.0 markdown returns { ok, outcome, hui, registry, blocks, diagnostics } where outcome is valid, violating, or unknown. ok false is a successful tool call so you can correct the document. Interactive blocks are zero tolerance: one error rejects the document. How to read and fix those diagnostics is in https://invokehumantool.com/skills/invoke-human/references/language.md.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "validate_ui"
  }
}

Input Schema

NameRequiredDescriptionDefault
uiNoHUI 0.1 document. You can also pass the document fields at the top level.
labsNoIgnored by validate_ui. Pass it to list_blocks to include labs. names.
lenientNoWhen true, unknown properties are warnings instead of errors.
markdownNoHUI 1.0 markdown. Fences and ih:// links are registry blocks.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / labs
      Added value: +{
      +  "description": "Ignored by validate_ui. Pass it to list_blocks to include labs. names.",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / markdown
      Added value: +{
      +  "description": "HUI 1.0 markdown. Fences and ih:// links are registry blocks.",
      +  "type": "string"
      +}
    • removedInput schema / required
      Removed value: -[
      -  "ui"
      -]
  2. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already cover readOnly/idempotent/non-destructive, yet the description adds real behavioral detail: exact return shapes per input format, the outcome enum values, the rule that ok=false is not a tool error, and the zero-tolerance policy for interactive blocks. That is precisely the non-obvious behavior an agent needs beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the identity of the tool, then packs return shapes, error semantics, and the strictness rule into a few dense sentences. No filler; the external reference link is the only deferral and it is placed last.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-required-parameter validation tool with no output schema, the description covers inputs, both response shapes, and failure semantics well enough to call it confidently. The diagnostics structure itself is punted to an external URL, which leaves a small gap for an offline agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baselines at 3. The description clarifies that the two input channels (HUI 0.1 document vs HUI 1.0 markdown) produce different response shapes, which is useful, but it adds nothing about 'lenient' or the ignored 'labs' parameter beyond what the schema already says.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Check a form') and immediately scopes it against the obvious sibling behavior: no handoff is created and no person is contacted, which distinguishes it from send_ui_handoff/delegate_handoff in the same family. An agent can select it without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'without creating a handoff and without contacting the person' implies the dry-run/pre-flight use case, and the note that ok=false is still a successful call tells the agent how to respond to failures. It never explicitly states 'call this before send_ui_handoff' or names a when-not condition, so context is clear but not fully prescriptive.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.