Cromanion

cromanion_grants

Read-only

List what your human has allowed this agent to do, and what they have not. Read this before assuming a capability — the alternative is discovering your permissions by failing in front of them. You cannot change these yourself; only your human can, in their console.

Input Schema

Name	Required	Description	Default
No arguments

Output Schema

Name	Required	Description
`ok`	Yes
`granted`	Yes	Only what you MAY do. A capability absent from this list is one to stop planning around.
`revoked`	Yes	True once your human has ended this credential. Nothing else will work; do not retry. The lists are then empty: a revoked credential is told nothing about the account.
`revokedAt`	No	When your human cut this credential off (ISO 8601). Present only when `revoked` is true.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 4, 2026

changedOutput schema / properties / revoked / description

Previous value: -"True once your human has ended this credential. Nothing else will work; do not retry."New value: +"True once your human has ended this credential. Nothing else will work; do not retry. The lists are then empty: a revoked credential is told nothing about the account."

addedOutput schema / properties / revokedAt

Added value: +{
+  "description": "When your human cut this credential off (ISO 8601). Present only when `revoked` is true.",
+  "type": "string"
+}

Changed1 schema field changedSep 6, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "granted": {
+      "description": "Only what you MAY do. A capability absent from this list is one to stop planning around.",
+      "items": {
+        "properties": {
+          "grant": {
+            "description": "The capability token, e.g. `goals`, matching what a refusal names in `neededGrant`.",
+            "type": "string"
+          },
+          "label": {
+            "description": "What your human saw when they allowed it.",
+            "type": "string"
+          }
+        },
+        "required": [
+          "grant"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "ok": {
+      "type": "boolean"
+    },
+    "revoked": {
+      "description": "True once your human has ended this credential. Nothing else will work; do not retry.",
+      "type": "boolean"
+    }
+  },
+  "required": [
+    "ok",
+    "revoked",
+    "granted"
+  ],
+  "type": "object"
+}

First observedSep 6, 2026

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 the safety profile is covered; the description adds the important boundary that these grants cannot be modified by the agent and only change in the human's console. It also conveys the consequence model (capability must be verified, not assumed), which the annotations do not express. Return format is not described, but an output schema exists, so that is not a real gap.

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 with a deliberate ordering: what the tool returns, when to call it, then the constraint that it is read-only. The motivational clause about failing in front of the human earns its place by making the calling trigger concrete rather than decorative.

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 zero-parameter read tool with an output schema and readOnly/openWorld annotations, the description covers purpose, timing, and the modification boundary. Nothing an agent needs in order 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.

Parameters4/5

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

The tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline for a no-param tool applies. No misleading parameter language is introduced.

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: "List what your human has allowed this agent to do, and what they have not," making it unmistakably a permissions/grants read. It is distinguishable from the many setter siblings (set_mode, set_voice, config) by framing the output as the human's allowances rather than agent-side configuration. It stops short of naming a specific sibling it might be confused with, which keeps it at 4.

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?

It gives an explicit trigger: "Read this before assuming a capability," plus a concrete cost of skipping it ("discovering your permissions by failing in front of them"). That is clear when-to-use guidance rather than vague implication. It does not name an alternative tool or state a when-not condition, so it falls short of the top band.

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

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.

Resources

Need Help?