figjam-context-mcp

Diagnose LLM Config

diagnose_llm_config

Read-only

Tests configured text and vision models with three synthetic JSON challenges, reporting semantic/schema failures after model/provider changes. May incur provider charges; does not read board content.

Instructions

Test the configured text and vision models with three small synthetic JSON challenges. Sends synthetic text and an image to the configured provider, may incur charges, and reports semantic/schema failures. Does not read board contents. Use after changing model/provider settings.

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": "diagnose_llm_config"
  }
}

Input Schema

Name	Required	Description	Default
No arguments

Output Schema

Name	Required	Description
`ok`	Yes
`checks`	Yes
`preset`	Yes
`summary`	Yes
`textModels`	Yes
`visionModels`	Yes
`fastTextModels`	Yes
`ignoredArguments`	No	Unknown input keys that were ignored; their values are not echoed. Absent when none
`providerRequireParameters`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.12.0Nov 5, 2026

addedOutput schema / properties / ignoredArguments

Added value: +{
+  "description": "Unknown input keys that were ignored; their values are not echoed. Absent when none",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

Changed1 schema field changedv0.10.2Oct 21, 2026

addedOutput schema / properties / checks / items / properties / attempts

Added value: +{
+  "description": "The model candidates tried, in order; error is the provider's message or the error",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "error": {
+        "type": "string"
+      },
+      "model": {
+        "type": "string"
+      },
+      "ok": {
+        "type": "boolean"
+      }
+    },
+    "required": [
+      "model",
+      "ok"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

Addedv0.4.0Oct 18, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Goes well beyond the annotations by warning that it sends synthetic text and an image to the configured provider and may incur charges — cost exposure is exactly the kind of thing readOnlyHint/openWorldHint do not convey. Reports failures rather than throwing, which is useful to know. It does not state whether provider credentials must already be configured or how long the test takes.

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?

Two sentences, front-loaded with the action, then cost/scope caveats, then the usage trigger. Every clause carries information an agent needs and nothing is repeated from the schema or annotations.

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

Completeness5/5

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

With zero parameters and an output schema present, the description only needs to cover what it does, what it touches, and when to call it — all three are present. The cost warning and the board-exclusion note close the remaining gaps an agent would otherwise have to guess at.

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

Parameters4/5

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

The tool takes no parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The description correctly refrains from inventing arguments.

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?

Names a specific verb and target (test the configured text and vision models) and pins down the mechanism (three small synthetic JSON challenges) plus what it reports (semantic/schema failures). An agent can distinguish it from the board-oriented siblings at a glance.

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?

Gives a clear trigger condition: 'Use after changing model/provider settings.' Also adds an explicit exclusion, 'Does not read board contents,' which separates it from ingest_board and get_board_context. No alternative-tool routing is stated, but the exclusions do most of the work.

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

Deploy Server