Skip to main content
Glama

Agent Broker

by dev.hatchloop
OverviewDiscussionsAdmin

send_message

Destructive

Send a message on behalf of an agent's user or an SMB across WhatsApp (free during launch), SMS, email, or voice, sent immediately with no scheduling. Every send routes through a non-bypassable gate (TCPA, GDPR, CASL, PDPL across 26 jurisdictions): marketing without recorded consent is rejected at runtime with a structured compliance_violation receipt. [from $0.02/call, variable] [async→get_outcome] [Not available on this deployment: SMS, Voice.]

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
contentYes
recipientYes
business_idNoStable id for the recipient business; used for global demand shaping.
message_typeYesIntent tag for the message. Five permitted types. 'marketing' is allowed only…
on_behalf_ofNoWho this message is FOR (your end-user's name/label). On WhatsApp this opens a…
idempotency_keyNoRetry key: a 24h replay returns the original receipt, not re-run or charged.
preferred_channelNoauto

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / business_id / description
      Previous value: -"Optional stable id for the recipient business. Enables global demand shaping…"New value: +"Stable id for the recipient business; used for global demand shaping."
    • changedInput schema / properties / idempotency_key / description
      Previous value: -"Optional client-supplied key for safe retries. Replaying the same key within 24h returns the original receipt - the operation is NOT re-executed and NOT re-charged."New value: +"Retry key: a 24h replay returns the original receipt, not re-run or charged."
    • removedInput schema / properties / send_at_iso
      Removed value: -{
-  "description": "NOT SUPPORTED YET. We do not schedule messages. Supplying a time more than 2…",
-  "format": "date-time",
-  "type": "string"
-}
  2. Changed4 schema fields changed
    • changedInput schema / properties / business_id / description
      Previous value: -"Optional stable id for the recipient business. Enables global demand shaping (we rate-limit total inbound across ALL agents so businesses stay responsive instead of blocking us)."New value: +"Optional stable id for the recipient business. Enables global demand shaping…"
    • changedInput schema / properties / message_type / description
      Previous value: -"Intent tag for the message. Five permitted types. 'marketing' is allowed only when paired with a valid consent_record_id; the compliance gate verifies the consent at send time and rejects (compliance_violation receipt) if it's missing, expired, or revoked."New value: +"Intent tag for the message. Five permitted types. 'marketing' is allowed only…"
    • changedInput schema / properties / on_behalf_of / description
      Previous value: -"Who this message is FOR (your end-user's name/label). On WhatsApp this opens a tracked conversation and travels in-message as '#4821 for Sara (via HatchLoop)', so the business knows who it is talking to and their reply is matched back to this exact request instead of guessed. Strongly recommended for two-way channels."New value: +"Who this message is FOR (your end-user's name/label). On WhatsApp this opens a…"
    • changedInput schema / properties / send_at_iso / description
      Previous value: -"NOT SUPPORTED YET. We do not schedule messages. Supplying a time more than 2 minutes in the future is REFUSED (reason_code scheduling_not_supported) rather than sent immediately, which is what used to happen. Call send_message at the moment you want delivery, or omit this field."New value: +"NOT SUPPORTED YET. We do not schedule messages. Supplying a time more than 2…"
  3. Changed1 schema field changed
    • changedInput schema / properties / send_at_iso / description
      Previous value: -"Schedule for future delivery; omit for immediate"New value: +"NOT SUPPORTED YET. We do not schedule messages. Supplying a time more than 2 minutes in the future is REFUSED (reason_code scheduling_not_supported) rather than sent immediately, which is what used to happen. Call send_message at the moment you want delivery, or omit this field."
  4. Changed2 schema fields changed
    • addedInput schema / properties / business_id
      Added value: +{
+  "description": "Optional stable id for the recipient business. Enables global demand shaping (we rate-limit total inbound across ALL agents so businesses stay responsive instead of blocking us).",
+  "type": "string"
+}
    • addedInput schema / properties / on_behalf_of
      Added value: +{
+  "description": "Who this message is FOR (your end-user's name/label). On WhatsApp this opens a tracked conversation and travels in-message as '#4821 for Sara (via HatchLoop)', so the business knows who it is talking to and their reply is matched back to this exact request instead of guessed. Strongly recommended for two-way channels.",
+  "type": "string"
+}
  5. Changed1 schema field changed
    • changedInput schema / properties / preferred_channel / enum
      Previous value: -[
-  "sms",
-  "email",
-  "voice",
-  "auto"
-]New value: +[
+  "whatsapp",
+  "sms",
+  "email",
+  "voice",
+  "auto"
+]
  6. Changed1 schema field changed
    • addedInput schema / properties / idempotency_key
      Added value: +{
+  "description": "Optional client-supplied key for safe retries. Replaying the same key within 24h returns the original receipt - the operation is NOT re-executed and NOT re-charged.",
+  "maxLength": 128,
+  "type": "string"
+}
  7. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already declare destructiveHint=true, openWorldHint=true, idempotentHint=false and readOnlyHint=false, but the description adds substantial behavior the annotations cannot convey: a non-bypassable TCPA/GDPR/CASL/PDPL gate across 26 jurisdictions, runtime rejection with a structured compliance_violation receipt, variable per-call cost, and an async pattern ('async→get_outcome'). This is exactly the extra context the bar asks for.

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 lead sentence, and the bracketed trailers (cost, async pattern, unavailable channels) are information-dense rather than filler. The telegraphic bracket style is slightly compressed and reads as metadata appendices rather than prose, which costs a point on structure but nothing is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 7-parameter destructive mutation with no output schema, the description covers the critical operational facts: compliance rejection behavior, cost, async retrieval path, and channel availability on this deployment. It does not cover auth/permission prerequisites or what a successful send returns, which would fully close the loop, but no agent-critical info 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 57%, so the description must carry part of the load, and it does: it explains the compliance-routing implication behind recipient/country_code, that 'marketing' is gated on recorded consent, and that on_behalf_of identifies who the message is for. It does not add meaning for template_id, template_vars, business_id, or idempotency_key beyond what the schema already says, leaving some room.

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 specific verb and resource (send a message) plus the actor (agent's user or SMB), the channels (WhatsApp/SMS/email/voice), and the timing constraint (immediately, no scheduling). An agent can distinguish this from the sibling send_transactional_confirmation and the read-only siblings without opening a 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 clear context for when this tool applies: immediate sends across four channels, with a hard compliance gate governing marketing message_type. It also flags deployment availability ('Not available on this deployment: SMS, Voice'), which materially changes routing decisions. It stops short of explicitly contrasting against send_transactional_confirmation, so it is not a full when/when-not/alternative statement.

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

All Agent Broker 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