Perisclaw: Use ChatGPT and Claude with your WhatsApp

Show reply card

workspace_conversation

Read-only

Use this when the user wants to reply to a WhatsApp chat. Shows a card with the latest messages and your draft; the user edits it and presses Send in the card, which sends it. Never call reply_prepare or reply_send for a draft shown in a card: if the user says "send it", tell them to press Send in the card. To change the draft, call this again with new draft_text. Resolve the chat first. Sends nothing by itself.

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": {
      "chat_id": "<chat_id>"
    },
    "name": "workspace_conversation"
  }
}

Input Schema

Name	Required	Description
`chat_id`	Yes	WhatsApp chat ID from search_chats or chats_recent.
`draft_text`	No	Your suggested reply, in WhatsApp formatting.
`quote_message_id`	No	Optional message_id to quote, from get_messages.

Output Schema

Name	Required	Description	Default
`chat`	Yes
`quoted`	Yes
`card_id`	Yes
`profile`	Yes
`messages`	Yes
`read_only`	Yes
`draft_text`	Yes
`quote_message_id`	Yes
`monitoring_available`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 2, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations declare readOnlyHint=true, and the description supports that rather than contradicting it: 'Sends nothing by itself' clarifies that sending happens via the user's Send press in the card, not through the tool call. It also discloses side effects of repeated calls (re-calling replaces the draft) and the required prior step of resolving the chat — context the annotations alone don't convey.

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?

The trigger is front-loaded and nearly every clause carries a rule. Two sentences circle the same prohibition (never call reply_prepare/reply_send, and redirect 'send it' to the card's button), which is mild redundancy in an otherwise dense, purposeful block.

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?

With an output schema present, return-value explanation is correctly omitted. The description covers the interaction model, the update path, the prerequisite, and what the tool does not do — nothing an agent needs in order to call it safely is missing.

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 baseline is 3, but the description adds meaning beyond the schema by specifying that draft_text is the mechanism for updating an existing card draft ('call this again with new draft_text'). quote_message_id and chat_id resolution are left to the schema, which handles them adequately.

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?

States a concrete verb and resource — it 'shows a card with the latest messages and your draft' for a WhatsApp chat — and immediately distinguishes itself from reply_prepare/reply_send, which it explicitly says are not the tool for a carded draft. An agent can tell exactly what this tool renders without opening the schema.

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?

Gives the trigger ('when the user wants to reply to a WhatsApp chat'), the exclusion ('Never call reply_prepare or reply_send for a draft shown in a card'), the response to a follow-up 'send it', the update path ('call this again with new draft_text'), and a prerequisite ('Resolve the chat first'). This is essentially a full decision procedure.

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

All Perisclaw: Use ChatGPT and Claude with your WhatsApp 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.