CallMCP — Phone Call MCP Server

Share Call Example

share_call_example

Idempotent

Owner only: publish a finished errand call as a redacted transcript example (no audio, business shown as a category). Call once for a preview, show it, then confirm with its preview_hash.

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>"
    },
    "name": "share_call_example"
  }
}

Input Schema

Name	Required	Description
`title`	No	Short title in the owner’s words, 120 characters or fewer. Personal details are removed (optional)
`errand`	No	The kind of errand, if one fits (optional)
`call_id`	Yes	The finished errand call to share
`confirm`	No	True only after the owner has seen the preview and asked to publish it. Without it nothing is published.
`outcome`	No	What happened, in the owner’s words, 600 characters or fewer. Defaults to the call summary (optional)
`preview_hash`	No	The preview_hash from the preview the owner approved. Required with confirm.
`business_category`	No	What kind of business was called, shown instead of its name (default business)

Output Schema

Name	Required	Description
`code`	No
`error`	No	Present when success is false
`preview`	No
`success`	Yes	Whether the tool completed successfully
`published`	No
`shared_at`	No
`examples_url`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 12, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Annotations only tell the agent this is a non-destructive, idempotent, open-world write. The description adds the data effects the agent actually needs: audio is excluded, the business name is replaced by a category, and nothing is published until a confirm plus a matching preview_hash arrive. It also states the authorization boundary ('Owner only'), which the annotations do not cover.

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?

Two sentences, no filler, and the highest-risk constraint (owner-only publication with redaction) is front-loaded before the workflow instruction. Every clause carries information an agent must act on.

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 7-parameter mutation tool with a 100%-covered schema and an output schema, the description supplies exactly what structured fields cannot: the two-step preview/confirm gate, the redaction guarantees, and the owner restriction. Return values need not be explained because an output schema exists.

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 coverage is 100%, so every parameter including the confirm/preview_hash coupling and the business_category default is already documented in the schema. The description reinforces preview_hash as the value returned by the first call and ties confirm to it, but adds no format, constraint, or fallback detail beyond that.

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 uses a specific verb and resource ('publish a finished errand call as a redacted transcript example') and pins the scope twice: 'Owner only' and 'finished errand call'. The parenthetical 'no audio, business shown as a category' makes the output shape unmistakable and separates it from the unshare sibling without needing its name.

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 a concrete two-phase protocol: call once for a preview, show it, then confirm with its preview_hash. That is explicit when-to-use guidance for the first and second invocation. It falls short of 5 only because it never names the counterpart operation (unshare_call_example) or says when not to publish at all.

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

All CallMCP — Phone Call MCP Server 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.