Skip to main content
Glama
Sign In

AccountHub

by ai.accounthub
OverviewDiscussionsAdmin

send_chatwork_message

Destructive

Post a message to a Chatwork room — sends for real, at most once per draft. Requires draft_fingerprint from create_chatwork_draft for this exact account/room/body; a missing or mismatching fingerprint is refused before anything is sent. Before calling, show the final body to the user and get an explicit yes. The same message (same account, room, text and reply target — even from a NEW draft) is refused for 24 hours after it was sent (chatwork_duplicate_send), and while an earlier attempt is in progress or ended unknown (chatwork_prior_send_unknown); re-drafting does not get around this. If the result is chatwork_delivery_unknown (timeout, dropped connection, unreadable response, server error) the message MAY have been posted: do NOT resend — open the room (read_chatwork_room) to check, and tell the user. allow_duplicate: true sends another copy: set it ONLY after checking the room AND getting the user's explicit confirmation that another copy is wanted — never on your own. chatwork_send_not_attempted means nothing went out (a step before sending failed) and trying again is safe.

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": {
      "room_id": "<room_id>",
      "body": "<body>",
      "draft_fingerprint": "<draft_fingerprint>"
    },
    "name": "send_chatwork_message"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyYesThe FINAL body exactly as returned by create_chatwork_draft and shown to the user.
accountNoChatwork account label (see list_accounts). Required when more than one Chatwork account is connected and connection_id is not given.
room_idYesChatwork room id (digits, from list_chatwork_rooms).
connection_idNoConnection id from list_chatwork_rooms / list_accounts. Takes precedence over `account` when two connections share a label.
allow_duplicateNoSet true ONLY after the user has checked the room AND explicitly confirmed a second send is wanted (after an unknown or duplicate result). Never set it on your own.
draft_fingerprintYesREQUIRED: draft_fingerprint from create_chatwork_draft for this exact account/room/body.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only supply destructiveHint=true and a title; the description carries the real behavioral load — at-most-once semantics, fingerprint refusal before any send, 24-hour duplicate suppression keyed on account/room/text/reply target (even across a new draft), refusal while a prior attempt is in progress or unknown, and per-error-code recovery guidance for chatwork_delivery_unknown / chatwork_prior_send_unknown / chatwork_send_not_attempted. No contradiction with destructiveHint, which the "sends for real" framing reinforces.

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?

Front-loaded with the core action and its at-most-once guarantee, and every subsequent sentence carries an operational rule rather than filler. It is dense — a long paragraph of error codes and gates — and would read faster as short bullets, but nothing is redundant.

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 6-parameter destructive tool with no output schema, the description supplies everything an agent needs to act safely: prerequisites, confirmation protocol, duplicate window, and a decision tree for each possible failure outcome. The error-code handling effectively stands in for the missing output schema.

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 100%, so the schema baseline alone would earn a 3. The description adds real meaning on top: draft_fingerprint is explained as a provenance binding to an exact draft, allow_duplicate is constrained to a specific post-verification scenario, and body is required to be the final body shown to the user. Only the account/connection_id precedence is left entirely to the schema.

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?

"Post a message to a Chatwork room — sends for real, at most once per draft" gives a specific verb, resource, and the key distinguishing property (real send, single-shot). It cleanly separates this tool from its sibling create_chatwork_draft (which produces the fingerprint this one consumes) and from the generic send_message/send_chat_message family.

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 states the preconditions (fingerprint from create_chatwork_draft for this exact account/room/body, show body and get an explicit yes) and names the alternative path for the unknown case (do not resend — use read_chatwork_room to check). It also gates allow_duplicate with a concrete two-part condition, so when-to-use and when-not-to-use are both spelled out.

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

All AccountHub toolsInspect
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.

Resources