Skip to main content
Glama

vote_poll

Vote on active Signal polls in DMs or groups. Send option indices with poll identifiers to cast or change your vote.

Instructions

Cast your vote on an active Signal poll in a DM or group conversation. Your vote is delivered via signal-cli and is visible to all participants in real time. Each participant can vote once; re-voting overwrites the previous selection. For single-choice polls, provide exactly one option index in votes. For multi-select polls, provide all chosen indices in a single call — partial updates are not supported. votes are 0-based indices corresponding to the options array from the original create_poll call. Get target_author, target_timestamp, and poll_id from the poll message returned by get_conversation. Provide exactly one of recipient (for a DM poll) or group_id (for a group poll). Voting on a terminated poll returns an error. Use terminate_poll to close a poll you created and freeze the results. Use when responding to an open poll in a conversation. Do NOT use to create a poll — use create_poll instead.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
target_authorYesPhone number of the poll creator (E.164)
target_timestampYesTimestamp of the poll message (from get_conversation)
poll_idYesPoll ID from the poll message data
votesYesOption indices to vote for (0-based). Single item for single-choice polls.
recipientNoPhone number for a DM poll — provide this OR group_id
group_idNoGroup ID for a group poll — provide this OR recipient

Implementation Reference

  • The vote_poll method on SignalClient: sends a vote on an existing poll via the sendPollVote JSON-RPC method. Requires target_author, target_timestamp, poll_id, and votes list, plus exactly one of recipient or group_id.
    async def vote_poll(
        self,
        target_author: str,
        target_timestamp: int,
        poll_id: int,
        votes: list[int],
        recipient: str | None = None,
        group_id: str | None = None,
    ) -> None:
        """Vote on an existing poll."""
        if not recipient and not group_id:
            raise SignalError("Either recipient or group_id must be provided")
        params: dict = {
            "targetAuthor": target_author,
            "targetTimestamp": target_timestamp,
            "poll-id": poll_id,
            "poll-answer": votes,
        }
        if group_id:
            params["groupId"] = group_id
        else:
            params["recipient"] = [recipient]
        await self._rpc("sendPollVote", params)
  • The call_tool handler for 'vote_poll': validates that recipient or group_id is provided, then calls client.vote_poll() with the arguments from the tool invocation.
    elif name == "vote_poll":
        if not arguments.get("recipient") and not arguments.get("group_id"):
            return _err("Either recipient or group_id is required")
        await client.vote_poll(
            target_author=arguments["target_author"],
            target_timestamp=arguments["target_timestamp"],
            poll_id=arguments["poll_id"],
            votes=arguments["votes"],
            recipient=arguments.get("recipient"),
            group_id=arguments.get("group_id"),
        )
        return _ok({"status": "vote sent"})
  • Tool registration for 'vote_poll': defines the input schema (target_author, target_timestamp, poll_id, votes arrays, recipient/group_id) and description.
    Tool(
        name="vote_poll",
        description=(
            "Cast your vote on an active Signal poll in a DM or group conversation. "
            "Your vote is delivered via signal-cli and is visible to all participants in real time. "
            "Each participant can vote once; re-voting overwrites the previous selection. "
            "For single-choice polls, provide exactly one option index in votes. "
            "For multi-select polls, provide all chosen indices in a single call — partial updates are not supported. "
            "votes are 0-based indices corresponding to the options array from the original create_poll call. "
            "Get target_author, target_timestamp, and poll_id from the poll message returned by get_conversation. "
            "Provide exactly one of recipient (for a DM poll) or group_id (for a group poll). "
            "Voting on a terminated poll returns an error. "
            "Use terminate_poll to close a poll you created and freeze the results. "
            "Use when responding to an open poll in a conversation. "
            "Do NOT use to create a poll — use create_poll instead."
        ),
        inputSchema={
            "type": "object",
            "properties": {
                "target_author": {"type": "string", "description": "Phone number of the poll creator (E.164)"},
                "target_timestamp": {"type": "integer", "description": "Timestamp of the poll message (from get_conversation)"},
                "poll_id": {"type": "integer", "description": "Poll ID from the poll message data"},
                "votes": {"type": "array", "items": {"type": "integer"}, "description": "Option indices to vote for (0-based). Single item for single-choice polls."},
                "recipient": {"type": "string", "description": "Phone number for a DM poll — provide this OR group_id"},
                "group_id": {"type": "string", "description": "Group ID for a group poll — provide this OR recipient"},
            },
            "required": ["target_author", "target_timestamp", "poll_id", "votes"],
        },
    ),
  • Required parameter validation entry for vote_poll: ensures target_author, target_timestamp, poll_id, and votes are present.
    "vote_poll":                      ["target_author", "target_timestamp", "poll_id", "votes"],
    "terminate_poll":                 ["target_author", "target_timestamp", "poll_id"],
Behavior5/5

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

Discloses real-time visibility, one vote per participant, re-voting overwrites, partial update unsupported for multi-select, target field sourcing from get_conversation, mutual exclusivity of recipient/group_id, and error on terminated poll. No annotations provided but description covers all behavioral aspects.

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?

Concise, well-structured, front-loads main action, each sentence adds value. No unnecessary words.

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?

Complete for a tool with 6 params, no output schema, no annotations. Covers usage, behavior, errors, and relationships to other tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Adds significant meaning beyond schema: explains 0-based indexing, relationship to get_conversation, single vs multi-select rule, and recipient/group_id exclusivity. Schema already has 100% coverage but description enriches understanding.

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?

Description clearly states the action (cast vote), resource (active Signal poll), and context (DM or group). It distinguishes from siblings like create_poll and terminate_poll.

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?

Explicitly says when to use (responding to open poll), when not to (terminated poll), and suggests alternatives (terminate_poll, create_poll). Provides prerequisites and clarifies single/multi-choice behavior.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/googlarz/signal-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server