MCP Operation Risk

MCP Operation Risk Check

evaluate_operation_risk

Read-onlyIdempotent

Check whether the actual operation inside an MCP tool call is safe before execution. Use this when one MCP tool exposes multiple operations with different side effects, so whole-tool permissions are too coarse. Provide the native MCP server identity, the tool's tools/list metadata and the intended arguments. For supported consolidated tools, distinguish read, create/add, update/mutate and delete/destructive operations. Return ALLOW, DENY, or REQUIRE_APPROVAL. Unknown, unsupported, ambiguous, or schema-changed calls fail closed with REQUIRE_APPROVAL. The evaluator never executes the source operation.

Input Schema

Name	Required	Description
`tool`	Yes	The complete relevant Tool record returned by the source server's tools/list.
`source`	Yes	MCP server and negotiated protocol identity for the source tool.
`arguments`	Yes	Arguments intended for the source MCP tools/call request being evaluated. The evaluator does not execute that call.

Schema Changelog

Changes observed during successful MCP inspections.

Changed16 schema fields changedOct 4, 2026

addedInput schema / properties / arguments / description

Added value: +"Arguments intended for the source MCP tools/call request being evaluated. The evaluator does not execute that call."

addedInput schema / properties / source / description

Added value: +"MCP server and negotiated protocol identity for the source tool."

addedInput schema / properties / source / properties / protocol_version / description
```
Added value: +"Negotiated MCP protocol version, or null when unavailable."
```

addedInput schema / properties / source / properties / server / description

Added value: +"MCP server identity from the connection's initialize response."

addedInput schema / properties / source / properties / server / properties / name / description

Added value: +"Name reported by the MCP server during initialize; used as a supported-manifest lookup hint."

addedInput schema / properties / source / properties / server / properties / version / description
```
Added value: +"Server version reported during initialize, or null when unavailable."
```

addedInput schema / properties / tool / description

Added value: +"The complete relevant Tool record returned by the source server's tools/list."

addedInput schema / properties / tool / properties / _meta / description

Added value: +"Relevant tool metadata from tools/list, when present."

addedInput schema / properties / tool / properties / annotations / description

Added value: +"Tool annotations from tools/list, such as read-only or destructive hints; use an empty object when absent."

addedInput schema / properties / tool / properties / description / description

Added value: +"Tool description from tools/list, or null if the server omitted it."

addedInput schema / properties / tool / properties / execution / description
```
Added value: +"Tool execution metadata from tools/list, when present."
```
addedInput schema / properties / tool / properties / icons / description
```
Added value: +"Tool icons from tools/list, when present."
```

addedInput schema / properties / tool / properties / inputSchema / description

Added value: +"Complete inputSchema from tools/list; used to validate the intended arguments and match a supported tool manifest."

addedInput schema / properties / tool / properties / name / description

Added value: +"Exact tool name from the MCP server's tools/list response."

addedInput schema / properties / tool / properties / outputSchema / description
```
Added value: +"Tool output schema from tools/list, when present."
```

addedInput schema / properties / tool / properties / title / description

Added value: +"Tool title from tools/list, when provided by the server."

Changed13 schema fields changedOct 4, 2026

removedInput schema / $defs

Removed value: -{
-  "NativeServerIdentity": {
-    "additionalProperties": false,
-    "properties": {
-      "name": {
-        "title": "Name",
-        "type": "string"
-      },
-      "version": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "title": "Version"
-      }
-    },
-    "required": [
-      "name",
-      "version"
-    ],
-    "title": "NativeServerIdentity",
-    "type": "object"
-  },
-  "NativeSource": {
-    "additionalProperties": false,
-    "properties": {
-      "protocol_version": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "title": "Protocol Version"
-      },
-      "server": {
-        "$ref": "#/$defs/NativeServerIdentity"
-      }
-    },
-    "required": [
-      "server",
-      "protocol_version"
-    ],
-    "title": "NativeSource",
-    "type": "object"
-  },
-  "NativeToolRecord": {
-    "additionalProperties": false,
-    "properties": {
-      "_meta": {
-        "anyOf": [
-          {
-            "additionalProperties": true,
-            "type": "object"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null,
-        "title": "Meta"
-      },
-      "annotations": {
-        "additionalProperties": true,
-        "title": "Annotations",
-        "type": "object"
-      },
-      "description": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "title": "Description"
-      },
-      "execution": {
-        "anyOf": [
-          {
-            "additionalProperties": true,
-            "type": "object"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null,
-        "title": "Execution"
-      },
-      "icons": {
-        "anyOf": [
-          {
-            "items": {
-              "additionalProperties": true,
-              "type": "object"
-            },
-            "type": "array"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null,
-        "title": "Icons"
-      },
-      "inputSchema": {
-        "additionalProperties": true,
-        "title": "Inputschema",
-        "type": "object"
-      },
-      "name": {
-        "title": "Name",
-        "type": "string"
-      },
-      "outputSchema": {
-        "anyOf": [
-          {
-            "additionalProperties": true,
-            "type": "object"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null,
-        "title": "Outputschema"
-      },
-      "title": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null,
-        "title": "Title"
-      }
-    },
-    "required": [
-      "name",
-      "description",
-      "inputSchema"
-    ],
-    "title": "NativeToolRecord",
-    "type": "object"
-  }
-}

removedInput schema / properties / source / $ref
```
Removed value: -"#/$defs/NativeSource"
```
addedInput schema / properties / source / additionalProperties
```
Added value: +false
```

addedInput schema / properties / source / properties

Added value: +{
+  "protocol_version": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "title": "Protocol Version"
+  },
+  "server": {
+    "additionalProperties": false,
+    "properties": {
+      "name": {
+        "title": "Name",
+        "type": "string"
+      },
+      "version": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "title": "Version"
+      }
+    },
+    "required": [
+      "name",
+      "version"
+    ],
+    "title": "NativeServerIdentity",
+    "type": "object"
+  }
+}

addedInput schema / properties / source / required

Added value: +[
+  "server",
+  "protocol_version"
+]

addedInput schema / properties / source / title
```
Added value: +"NativeSource"
```
addedInput schema / properties / source / type
```
Added value: +"object"
```
removedInput schema / properties / tool / $ref
```
Removed value: -"#/$defs/NativeToolRecord"
```
addedInput schema / properties / tool / additionalProperties
```
Added value: +false
```

addedInput schema / properties / tool / properties

Added value: +{
+  "_meta": {
+    "anyOf": [
+      {
+        "additionalProperties": true,
+        "type": "object"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "title": "Meta"
+  },
+  "annotations": {
+    "additionalProperties": true,
+    "title": "Annotations",
+    "type": "object"
+  },
+  "description": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "title": "Description"
+  },
+  "execution": {
+    "anyOf": [
+      {
+        "additionalProperties": true,
+        "type": "object"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "title": "Execution"
+  },
+  "icons": {
+    "anyOf": [
+      {
+        "items": {
+          "additionalProperties": true,
+          "type": "object"
+        },
+        "type": "array"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "title": "Icons"
+  },
+  "inputSchema": {
+    "additionalProperties": true,
+    "title": "Inputschema",
+    "type": "object"
+  },
+  "name": {
+    "title": "Name",
+    "type": "string"
+  },
+  "outputSchema": {
+    "anyOf": [
+      {
+        "additionalProperties": true,
+        "type": "object"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "title": "Outputschema"
+  },
+  "title": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "title": "Title"
+  }
+}

addedInput schema / properties / tool / required

Added value: +[
+  "name",
+  "description",
+  "inputSchema"
+]

addedInput schema / properties / tool / title
```
Added value: +"NativeToolRecord"
```
addedInput schema / properties / tool / type
```
Added value: +"object"
```

AddedOct 4, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Annotations already declare readOnlyHint/idempotent/non-destructive, and the description is consistent with them ('the evaluator never executes the source operation'). It goes well beyond by disclosing the decision vocabulary (ALLOW, DENY, REQUIRE_APPROVAL) and the fail-closed behavior for unknown, unsupported, ambiguous, or schema-changed calls.

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?

Front-loaded with the core action, then the trigger condition, required inputs, and return/failure semantics in tight, waste-free sentences. Every sentence carries decision-relevant information for the caller.

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 read-only evaluation tool with no output schema, the description supplies the missing return contract (ALLOW/DENY/REQUIRE_APPROVAL) and the fail-closed policy. Combined with 100% schema coverage on a nested-object input, nothing an agent needs to call it correctly is absent.

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?

Schema description coverage is 100%, so the schema already documents all three parameters and the baseline is 3. The description adds value by tying each input to its semantic role ('native MCP server identity, the tool's tools/list metadata and the intended arguments') and by noting the arguments are not executed.

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?

States a specific verb and object: 'Check whether the actual operation inside an MCP tool call is safe before execution,' with a clear scoping rationale about per-operation vs whole-tool permissions. It is easy to tell apart from a generic safety tool, but it never names the sibling describe_operation_risk_service, so differentiation from that specific tool is left to inference.

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 an explicit trigger condition: use it 'when one MCP tool exposes multiple operations with different side effects, so whole-tool permissions are too coarse,' and tells the caller what inputs to supply. It stops short of naming the alternative tool or stating when not to use this one, so it is strong context without full routing.

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

All MCP Operation Risk tools Inspect

Try in Browser

Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?