Charming

mutate_app

Destructive

Run a mutating backend operation on a Charming app and return its result, without editing code. Use this for operations that change state — including operations whose read/write safety can't be determined. For read-only operations, use query_app. If you don't know an operation's name or which tool it needs, call get_app — each operation lists its tool.

Input Schema

TableJSON Schema

Name	Required	Description
`op`	Yes	Operation name, routed to /api/:op inside the app module
`app_id`	Yes	The app ID (UUID)
`params`	No	Optional JSON params

Output Schema

TableJSON Schema

Name	Required	Description
`ok`	Yes	True if the operation handler returned a successful envelope. False when the app reported an operation error — distinct from a transport/protocol error.
`error`	No	Set when ok=false. Always inspect kind before retrying.
`value`	No	Operation return value when ok=true. Shape depends on the app and op called.
`advisories`	No	Structured non-fatal advisories, including authoring issues and unread staff feedback responses. Each advisory.summary is also appended to the text content for the LLM path.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 10, 2026

addedOutput schema / properties / advisories

Added value: +{
+  "description": "Structured non-fatal advisories, including authoring issues and unread staff feedback responses. Each advisory.summary is also appended to the text content for the LLM path.",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "data": {
+        "additionalProperties": {},
+        "description": "Kind-specific structured payload. Shape varies per advisory kind.",
+        "propertyNames": {
+          "type": "string"
+        },
+        "type": "object"
+      },
+      "doc_url": {
+        "description": "Optional docs pointer for this advisory kind.",
+        "type": "string"
+      },
+      "kind": {
+        "description": "Stable advisory identifier (e.g. \"legacy-bridge\").",
+        "type": "string"
+      },
+      "severity": {
+        "description": "Severity; omitted advisories are treated as 'info'.",
+        "enum": [
+          "info",
+          "warn"
+        ],
+        "type": "string"
+      },
+      "summary": {
+        "description": "Agent-facing summary. Self-sufficient; no extra context required.",
+        "type": "string"
+      },
+      "userSummary": {
+        "description": "End-user-facing summary. Set when the advisory should render in-app.",
+        "type": "string"
+      }
+    },
+    "required": [
+      "kind",
+      "summary"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

First observedJul 15, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already flag readOnlyHint=false and destructiveHint=true; the description adds useful nuance by covering operations whose read/write safety cannot be determined, stating that it returns the operation result, and clarifying that it does not edit code. No contradictions with 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?

Three sentences: the primary action, the selection rule for when to use it, and the disambiguation fallback via get_app. Front-loaded and without redundant schema repetition.

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?

The description fully resolves the key agent decision—when to choose this tool over query_app and how to resolve unknown operations via get_app. With an output schema present and only three parameters, no further information is needed.

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 parameters are already fully described. The description reinforces that op is an operation name and that params are part of the operation, but it doesn't add much beyond the schema.

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?

The description opens with a specific verb and object: 'Run a mutating backend operation on a Charming app and return its result, without editing code.' It is immediately distinguishable from read-only siblings, and it tells the agent that this tool is for state-changing work rather than source editing.

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

Usage Guidelines5/5

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

Explicitly directs agents to use this tool for state-changing operations, including ambiguous ones, and to use query_app for read-only operations. It also tells agents to call get_app when the operation or tool is unknown, covering the main routing ambiguity.

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

All Charming tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.