Call Me

Hang up

hang_up

Destructive

End a call you placed. In an open conversation goodbye is spoken first; leave it empty to just hang up. A call that already ended reports its final status.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "call_id": "<call_id>",
      "session_token": "<session_token>"
    },
    "name": "hang_up"
  }
}

Input Schema

Name	Required	Description
`call_id`	Yes	The call_id from the call or play_audio result.
`goodbye`	No	Spoken before the line drops in an open conversation, e.g. "Thanks, I'll get on it." Empty just hangs up.
`session_token`	Yes	The session_token from an earlier result. It keeps every call and text in one thread on their phone.

Output Schema

Name	Required	Description
`open`	No	Always false: the line is down.
`status`	Yes	"ended", or "hanging_up" while the goodbye is spoken.
`call_id`	No	The call that was ended.
`session_token`	No	This session's token.

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedNov 4, 2026

addedInput schema / properties / call_id / description

Added value: +"The call_id from the call or play_audio result."

addedInput schema / properties / goodbye / description

Added value: +"Spoken before the line drops in an open conversation, e.g. \"Thanks, I'll get on it.\" Empty just hangs up."

addedInput schema / properties / session_token / description

Added value: +"The session_token from an earlier result. It keeps every call and text in one thread on their phone."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "properties": {
+    "call_id": {
+      "anyOf": [
+        {
+          "type": "integer"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "description": "The call that was ended.",
+      "title": "Call Id"
+    },
+    "open": {
+      "anyOf": [
+        {
+          "type": "boolean"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "description": "Always false: the line is down.",
+      "title": "Open"
+    },
+    "session_token": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "description": "This session's token.",
+      "title": "Session Token"
+    },
+    "status": {
+      "description": "\"ended\", or \"hanging_up\" while the goodbye is spoken.",
+      "title": "Status",
+      "type": "string"
+    }
+  },
+  "required": [
+    "status"
+  ],
+  "title": "HangUpResult",
+  "type": "object"
+}

AddedOct 17, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already flag destructiveHint=true, readOnlyHint=false, and idempotentHint=false, so the description's added value is the sequencing detail (goodbye is spoken before the line drops) and the note that an already-ended call returns its final status rather than erroring. That is genuine behavioral context beyond the structured fields, though it doesn't say whether the goodbye consumes time or what side effects occur on the remote end.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loading the action, then the goodbye behavior, then the already-ended edge case. Efficient, though the phrasing is slightly clipped and the second sentence reads as a fragment.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With rich annotations, a full output schema, and 100% parameter coverage, the description covers everything needed to invoke it correctly. The only gap is what the returned final status looks like or whether follow-up tools are required, which the output schema presumably handles.

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%, so all three parameters are documented in the schema, and the description largely restates the goodbye parameter's behavior. Baseline 3 applies since the schema carries the parameter semantics.

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?

States a specific verb and resource with scope: "End a call you placed." This distinguishes it cleanly from placement/oration siblings such as call, say, and play_audio — an agent can tell this is the terminal action for an existing call.

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?

Makes clear this applies to calls the agent itself placed and describes the two modes (with a goodbye line vs. immediate drop), plus what happens when the call is already over. It does not name alternatives, e.g. whether to use say first instead of passing goodbye, but the context is otherwise unambiguous.

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

All Call Me 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.