Cromanion

cromanion_set_mode

Idempotent

Switch the agent on. learn watches and shows visitors nothing; act lets it intervene in your human's name. customizeMode is a separate axis for rewriting their own page copy: off, shadow (propose only) or live. Needs the activation permission.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`mode`	No	`learn` watches and shows visitors nothing; `act` lets the agent intervene in your human's name. Omit to leave it as it is.
`customizeMode`	No	Rewriting your human's own page copy, a separate axis from `mode`: `off`, `shadow` (propose only, nothing shown) or `live`. Omit to leave it as it is.

Output Schema

TableJSON Schema

Name	Required	Description
`ok`	Yes
`mode`	Yes	The mode as it now stands.
`changed`	Yes	False when it already was what you asked for. Not a failure.
`customizeMode`	No

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

Changed1 schema field changedSep 6, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "changed": {
+      "description": "False when it already was what you asked for. Not a failure.",
+      "type": "boolean"
+    },
+    "customizeMode": {
+      "enum": [
+        "off",
+        "shadow",
+        "live"
+      ],
+      "type": "string"
+    },
+    "mode": {
+      "description": "The mode as it now stands.",
+      "enum": [
+        "learn",
+        "act"
+      ],
+      "type": "string"
+    },
+    "ok": {
+      "type": "boolean"
+    }
+  },
+  "required": [
+    "ok",
+    "changed",
+    "mode"
+  ],
+  "type": "object"
+}

Changed2 schema fields changedSep 6, 2026

addedInput schema / properties / customizeMode / description

Added value: +"Rewriting your human's own page copy, a separate axis from `mode`: `off`, `shadow` (propose only, nothing shown) or `live`. Omit to leave it as it is."

addedInput schema / properties / mode / description

Added value: +"`learn` watches and shows visitors nothing; `act` lets the agent intervene in your human's name. Omit to leave it as it is."

First observedSep 6, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already flag the tool as non-read-only and idempotent. The description adds meaningful behavioral context beyond the schema: `act` mode lets the agent intervene 'in your human's name', `learn` shows visitors nothing, and `customizeMode` is a separate axis with a propose-only option. It also discloses the activation-permission requirement. No contradiction with 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?

The description is compact and front-loaded with the core action ('Switch the agent on'), then efficiently explains both parameter axes and the permission requirement. Every sentence contributes necessary information without redundancy.

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?

For a tool with two optional enum parameters, full schema coverage, an output schema, and relevant annotations, the description is complete enough. It covers both parameters, the relationship between them, the permission requirement, and the behavioral stakes of `act` mode. Nothing critical is missing.

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 description coverage is 100%, and the tool description largely paraphrases the schema's parameter descriptions. It adds the useful framing that `customizeMode` is a separate axis, but does not provide materially new semantic detail beyond what the input schema already contains, so the baseline of 3 applies.

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 clearly states the tool's function: 'Switch the agent on' and then defines the two independent axes (`mode` and `customizeMode`) with their concrete values. This distinguishes it from siblings like `cromanion_set_voice` or `cromanion_set_brand`, which clearly target different resources.

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

Usage Guidelines3/5

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

The description gives clear context for what each mode does and notes the activation-permission prerequisite, but it does not explicitly compare against alternatives or state when not to use this tool. Usage is implied rather than explicitly scoped relative to sibling tools.

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

All Cromanion tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4/5.0

Disambiguation4/5

Most tools target a distinct resource or workflow, and the set_*/add_*/claim_* groups are well separated by their descriptions. The main risk is the cluster of open_claim, verify_claim, and claim_domain, but their lifecycle roles are clearly differentiated.

Naming Consistency4/5

All tools share the cromanion_ prefix and use snake_case, with a strong verb_noun pattern in actions like set_brand, add_goal, and verify_claim. A few resource-style names such as impact, pending, site_status, and surfaces break the pattern slightly, but not enough to cause real confusion.

Tool Count4/5

17 tools is slightly above the usual 3-15 range, but the server covers onboarding, configuration, approvals, measurement, and billing, and each tool addresses a distinct operation. No tool feels redundant, so the count is defensible if a bit heavy.

Completeness3/5

The core workflows are covered: claim/verify, configure, review pending items, decide, and read impact. However, there are no read/retrieve endpoints for current brand, voice, mode, holdout, or goal settings, and add_goal lacks a matching list/delete operation, leaving agents unable to audit or undo configuration.

Resources

Need Help?