Skip to main content
Glama

Call card action

call_card_action
Destructive

Call card only: the person's own taps. end_call hangs up and answer_question answers the phone agent's question, exactly as hangup_call and reply_on_call do; ui records a card interaction.

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": {
      "action": "<action>",
      "card_id": "<card_id>"
    },
    "name": "call_card_action"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoui only: the interaction.
finalNoanswer_question only. Default true.
actionYes
answerNoanswer_question only.
detailNoui only: the interaction's detail.
call_idNoRequired for end_call and answer_question.
card_idYes
question_idNoanswer_question only.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true, readOnlyHint=false and openWorldHint=true, so the risk profile is carried structurally; the description adds that end_call actually hangs up a live call and that answer_question injects a response into a live phone agent interaction. It does not say what happens to an in-flight call after hangup, whether answer_question is irreversible, or how `ui` events affect state. Given the annotations cover safety, the added behavioral mapping is useful but thin.

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?

One compact sentence-plus-clause with the scope restriction front-loaded before the per-action breakdown; a semicolon keeps the action mapping tight. Every phrase corresponds to a real distinction. 'the person's own taps' is the only slightly opaque wording, since it encodes 'user-initiated' indirectly.

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

Completeness3/5

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

An output schema exists, so return values need no explanation. However, this is a destructive, open-world tool with 8 parameters, a nested `detail` object and a required `card_id`, and the description never explains the two branches beyond naming them — nothing about when `ui` should be used versus the two call-affecting actions, or how the nested detail payload should be shaped. Adequate as a routing hint, incomplete for correct invocation of all three branches.

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 75%, close to the point where the schema does the heavy lifting, and the schema already describes name, final, answer, call_id, question_id and detail. The description's real contribution is disambiguating the three `action` enum values and their effects, which is worth something. It says nothing about `card_id` (required) or how `detail`/`name` are used for the `ui` branch, so it does not fully compensate for the remaining gap.

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 scope statement ('Call card only: the person's own taps') then enumerates the three accepted actions and the effect of each ('end_call hangs up', 'answer_question answers the phone agent's question', 'ui records a card interaction'). That is a clear verb-plus-resource account an agent can act on. It falls short of 5 only because the leading clause is terse and the tool's identity as a call-card action tool is implied rather than stated as a verb.

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?

'Call card only' is an explicit gating condition, and pairing it with 'exactly as hangup_call and reply_on_call do' tells the agent that those siblings are the non-card equivalents. That covers both when to use this tool and which alternative applies outside the card. It stops short of an explicit 'if you are not operating on a card, use hangup_call instead' instruction, leaving the routing to inference.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.