Skip to main content
Glama
PhononX

Carbon Voice

by PhononX
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

get_ai_action_responses

Read-only

Retrieve previously generated AI Action results for Carbon Voice conversations. Use to access existing outputs instead of running a new action, filtering by conversation, message, or prompt.

Instructions

Retrieve AI Action results that were generated previously. USE WHEN: You want existing output rather than a fresh run — e.g. showing what an AI Action already produced for a message or conversation. Combine prompt_id, message_id and channel_id to narrow. USE INSTEAD: run_ai_action (or summarize_conversation) to generate new output; this tool only reads what already exists and returns an empty array if nothing has been generated. EXAMPLE: {"channel_id":"conv-abc","limit":10} RETURNS: Array of {id, prompt_id, creator_id, message_ids, channel_id?, workspace_id?, responses: [{language, text?, markdown?, html?, json?}], created_at}. NARROW: pass response_fields ["id","prompt_id","responses"] unless you need more — the full payload is much larger.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dateNoISO 8601 anchor timestamp; pair with `direction` to page.
limitNoMax responses to return.
directionNo
prompt_idNoOnly responses generated by this AI Action, from `list_ai_actions`.
channel_idNoOnly responses in this conversation, from `list_conversations`.
message_idNoOnly responses about this message, from `list_messages`.
response_fieldsNoDot-path allowlist to shrink the response, e.g. ["results.id","total"]. Omit for the full payload.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv2.10.0
    • addedInput schema / properties / channel_id / description
      Added value: +"Only responses in this conversation, from `list_conversations`."
    • addedInput schema / properties / date / description
      Added value: +"ISO 8601 anchor timestamp; pair with `direction` to page."
    • addedInput schema / properties / limit / description
      Added value: +"Max responses to return."
    • addedInput schema / properties / message_id / description
      Added value: +"Only responses about this message, from `list_messages`."
    • addedInput schema / properties / prompt_id / description
      Added value: +"Only responses generated by this AI Action, from `list_ai_actions`."
    • addedInput schema / properties / response_fields
      Added value: +{
+  "description": "Dot-path allowlist to shrink the response, e.g. [\"results.id\",\"total\"]. Omit for the full payload.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}
  2. First observed

TDQS

A4.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description doesn't need to restate safety. It adds meaningful behavioral context beyond that: the return format, the fact that an empty array is returned if no data exists, and a warning that the full payload is much larger and can be shrunk with response_fields. This gives the agent a good sense of what to expect, though it doesn't explicitly explain the date/direction pagination mechanics (those are in the schema but not described in prose).

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?

The description is tightly organized with labeled sections (USE WHEN, USE INSTEAD, EXAMPLE, RETURNS, NARROW) and every sentence contributes. The core purpose is front-loaded, and the example is compact. There is zero filler.

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?

Given the tool is a simple read-only retriever with no output schema, the description fully covers what an agent needs: what it does, when to use it, how to narrow results, what the return looks like, and a performance tip. The absence of a documented output schema is mitigated by the explicit RETURNS section. It is complete for correct invocation.

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 coverage is 86%, so the schema already documents most parameters. The description adds value by explaining the combined use of prompt_id, message_id, and channel_id to narrow results, and by clarifying that response_fields is an allowlist to shrink the payload. The example demonstrates a realistic usage. This exceeds the baseline for high schema coverage.

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 opens with a clear, specific verb-resource statement: 'Retrieve AI Action results that were generated previously.' It immediately distinguishes itself from run_ai_action by noting it only reads existing output, and it lists the narrowing fields. This makes the tool's purpose unambiguous and differentiates it from siblings like run_ai_action and summarize_conversation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit 'USE WHEN' and 'USE INSTEAD' sections, telling the agent exactly when to pick this tool (when existing output is wanted) and when to pick alternatives (run_ai_action or summarize_conversation for fresh generation). It also gives a concrete example and notes that an empty array is returned if nothing exists, which sets expectations clearly.

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

Deploy Server

Other Tools