Skip to main content
Glama

Validate a diagram

validate_diagram
Read-only

Validate a Fluxygram diagram before sharing: checks it with the same validator the viewer uses and returns either a valid summary or every problem with its path so you can fix it.

Instructions

Checks a Fluxygram diagram with the same validator the viewer uses. Returns "valid" with a short summary, or every problem with its path so you can fix it. Always validate before sharing.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "diagram": "<diagram>"
    },
    "name": "validate_diagram"
  }
}

Input Schema

NameRequiredDescriptionDefault
langNoLanguage of the error messages. Default en.
diagramYesThe diagram: the JSON object or its text.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered structurally; the description adds the non-obvious behavioral detail that it runs the identical validator as the viewer and that failure returns every problem individually with a path rather than a single opaque error. It does not mention diagram size or complexity limits, or whether validation has any side effects on stored diagrams — a modest remaining gap for a zero-annotation burden that is largely already discharged.

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?

Three short sentences, zero filler: identity first, then the two possible return shapes, then the action directive. No restating of the name or title, and nothing stale or padded.

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?

With no output schema, the description usefully front-loads both return shapes (bare 'valid' plus summary, or per-problem paths), and it sets the workflow expectation. For a two-parameter read-only validator this is nearly complete; only edge behavior such as size limits or handling of malformed JSON vs semantic errors is left unstated.

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 both parameters (diagram, lang) are already documented in the schema, including the en/es enum. The description adds nothing about the accepted input forms beyond calling it a 'Fluxygram diagram' and never mentions the error-message language option. Baseline 3 is appropriate when the schema does the heavy lifting.

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?

"Checks a Fluxygram diagram with the same validator the viewer uses" names a specific verb (checks), a specific resource (a Fluxygram diagram), and pins down the exact semantics — validator parity with the viewer — which no sibling (get_example, get_guide, share_link) provides. An agent can distinguish this from the other tools 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?

"Always validate before sharing" gives an explicit workflow directive that sequences this tool ahead of the share_link sibling, and the return-value sentence ("so you can fix it") implies the iterate-and-fix loop. It stops short of naming share_link as the alternative or stating when validation can be skipped, so it is clear context rather than a full when/when-not map.

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

Deploy Server

Other Tools