Cromanion

cromanion_set_voice

DestructiveIdempotent

Write the facts the agent may state to visitors, and the things it must never say. Plain sentences, one idea per line; start a line with 'never' to forbid something. Anything you write that your human's own pages do not already state is attributed to THEM as the source — so write only what they have told you is true. Every rule is checked against your own text and the site's vocabulary, and anything ungrounded is silently dropped: read the returned lines to see what actually survived. Your human sees each line attributed to you. Needs the voice permission.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`text`	Yes	The whole guidance, replacing what is there. An empty string clears it.
`siteId`	No	Which site this call is about. Only needed when your credential covers more than one — cromanion_grants lists them and says whether it is required. Omitting it with several is refused rather than guessed at.

Output Schema

TableJSON Schema

Name	Required	Description
`ok`	Yes
`lines`	Yes	What SURVIVED grounding, not what you sent. Compare it with your input; anything missing was dropped as unverifiable.
`cleared`	No	Present when you sent an empty string: the guidance is now empty.

Schema Changelog

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

Changed1 schema field changedSep 7, 2026

addedInput schema / properties / siteId

Added value: +{
+  "description": "Which site this call is about. Only needed when your credential covers more than one — cromanion_grants lists them and says whether it is required. Omitting it with several is refused rather than guessed at.",
+  "type": "string"
+}

Changed1 schema field changedSep 6, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "cleared": {
+      "description": "Present when you sent an empty string: the guidance is now empty.",
+      "type": "boolean"
+    },
+    "lines": {
+      "description": "What SURVIVED grounding, not what you sent. Compare it with your input; anything missing was dropped as unverifiable.",
+      "items": {
+        "properties": {
+          "backedBy": {
+            "description": "What vouches for it — the site's own pages, or your human's assertion through you.",
+            "type": "string"
+          },
+          "concepts": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "kind": {
+            "description": "Whether it asserts a fact or forbids a phrase.",
+            "type": "string"
+          },
+          "raw": {
+            "description": "The sentence, as you wrote it.",
+            "type": "string"
+          }
+        },
+        "required": [
+          "raw",
+          "kind"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "ok": {
+      "type": "boolean"
+    }
+  },
+  "required": [
+    "ok",
+    "lines"
+  ],
+  "type": "object"
+}

First observedSep 6, 2026

TDQS

A4.2/5.0

Behavior5/5

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

Beyond the destructive and idempotent hints, the description discloses that ungrounded rules are silently dropped, that each line is attributed to the human, that an empty string clears the voice, and that replacement is full rather than additive. It also calls out the required voice permission and that the returned lines show what survived. This is rich behavioral context beyond 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 dense but every sentence earns its place: purpose, line syntax, attribution, validation/drop behavior, output meaning, and permission. It is front-loaded with the core purpose before the mechanics.

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 destructive, idempotent write operation with an output schema, the description fully covers purpose, input format, side effects, error behavior (refusal to guess), permissions, and how to read the result. Nothing an agent needs to call it correctly is missing.

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

Parameters5/5

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

Despite 100% schema coverage, the description substantially enriches both parameters: text gets a line format with 'never' prefixes and empty-string clearing semantics, while siteId gets a clear rule about when it is required and that omission with multiple credentials is refused. This goes well beyond the schema's short descriptions.

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

Purpose4/5

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

The description opens with a specific verb and resource: 'Write the facts the agent may state to visitors, and the things it must never say,' which clearly identifies the tool as setting the agent's voice/facts. It is further clarified by the title 'Replace the facts the agent may state'. However, it does not explicitly differentiate itself from sibling set_* tools like cromanion_set_brand or cromanion_set_playbook, so it stops short of full sibling distinction.

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

Usage Guidelines2/5

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

The description provides strong how-to guidance but no explicit when-to-use or when-not-to-use guidance, and it never names an alternative tool. There is no exclusion criteria such as 'use cromanion_set_brand for brand voice instead' or prerequisite context like which other tools to prefer. This leaves selection among the many sibling set_* tools mostly to inference.

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

Disambiguation5/5

Each tool maps to a distinct resource or action—state reads (config, pending, grants, site_status), mutations (set_*, add_goal, decide), and lifecycle steps (open_claim, verify_claim, claim_domain) are clearly separated by detailed descriptions. Even similar-sounding tools like install_check vs site_status are explicitly differentiated.

Naming Consistency3/5

All tools share the cromanion_ prefix and snake_case, but the action-object pattern is inconsistent: many are verb_noun (set_mode, verify_claim), while others are bare nouns or verbs (config, pending, crawl, decide, surfaces). This mixed convention is readable but not predictable.

Tool Count3/5

24 tools is at the high end; the server covers a broad domain and each tool has a distinct job, but the set feels heavy with many narrow configuration endpoints (set_brand, set_voice, surfaces, exclusions). It is not bloated enough to be chaotic, but it is borderline.

Completeness4/5

The surface covers the full lifecycle from claim/verify/install through goal definition, rules, decisions, measurement, and lead delivery. Minor gaps exist—no account/site deletion, no broader integration management—but agents can accomplish core workflows without dead ends.

Resources

Need Help?