Skip to main content
Glama
Sign In

Send4

by ai.send4
OverviewDiscussionsAdmin

Rehearse a flow

rehearse_flow
Destructive

Play a flow as the customer on Send4's simulator. No real customer is texted. To start: flow_id and mode: inbound (first message in say), campaign (list columns in context), webhook (request body in payload) or web_chat. Works on drafts. To reply: conversation_id and say. To fast-forward: conversation_id and control (skip_wait ends a wait card's timer, end_tail closes the follow-up window). The AI takes a few seconds: read the answer with read_rehearsal. It spends the AI allowance, and webhook, email and Hanna cards send for real, marked as tests.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "rehearse_flow"
  }
}

Input Schema

NameRequiredDescriptionDefault
sayNoWhat the customer writes.
modeNoDefaults to inbound.
contextNo`campaign` mode: the list columns.
controlNoWith `conversation_id`.
flow_idNoTo start: from `list_flows`.
payloadNo`webhook` mode: the request body.
conversation_idNoTo go on: from an earlier answer of this tool.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • addedInput schema / properties / context / description
      Added value: +"`campaign` mode: the list columns."
    • addedInput schema / properties / control / description
      Added value: +"With `conversation_id`."
    • addedInput schema / properties / conversation_id / description
      Added value: +"To go on: from an earlier answer of this tool."
    • addedInput schema / properties / flow_id / description
      Added value: +"To start: from `list_flows`."
    • addedInput schema / properties / payload / description
      Added value: +"`webhook` mode: the request body."
    • addedInput schema / properties / say / description
      Added value: +"What the customer writes."
  2. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations flag destructiveHint=true and openWorldHint=true, and the description earns credit by explaining what that actually means: nothing is texted to a real customer, but 'webhook, email and Hanna cards send for real, marked as tests'. It also discloses latency ('the AI takes a few seconds'), cost ('It spends the AI allowance') and read-back behavior, which no annotation conveys.

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?

Front-loaded with the core distinction (simulator, no real customer), then structured as three labeled usage clauses, then side-effect warnings. Telegraphic and every sentence carries either routing or risk information; nothing is 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?

For a 7-parameter, multi-mode, destructive-ish tool with no output schema, the description covers entry conditions, continuations, cost, latency, side effects, and where to read results (read_rehearsal). 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 the mode-to-payload mapping (inbound uses 'say', campaign uses list columns in 'context', webhook uses the request body in 'payload') and the mutually exclusive start/reply/control argument sets that the flat schema cannot express. Some of this duplicates schema text ('from `list_flows`', 'With `conversation_id`'), which holds it off a 5.

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?

Opens with a specific verb and resource pair ('Play a flow as the customer on Send4's simulator') and immediately scopes it ('No real customer is texted'), which separates it from check_flow, read_flow, preview_flow_status and start_conversation. An agent can tell this is a draft-testing simulator rather than a live-conversation tool 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 Guidelines4/5

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

Gives explicit invocation patterns keyed to argument combination: 'To start' (flow_id + mode), 'To reply' (conversation_id + say), 'To fast-forward' (conversation_id + control), plus the note that it 'Works on drafts'. It also routes the follow-up read to read_rehearsal. The only gap is the absence of an explicit when-not/versus-sibling statement (e.g. versus check_flow for static validation).

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

All Send4 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