Skip to main content
Glama

Sweeppea MCP

by com.sweeppea.mcp
OverviewDiscussionsAdmin

send_message

Queue ONE email and/or SMS, written by you, to one of your OWN participants. SENDS A REAL MESSAGE — it leaves the platform and cannot be recalled. There is no address field: the recipient is a participant token inside the account, so this cannot be used to message anyone else. confirm=true is REQUIRED; set it only after the user approved the exact text going to that participant. Plain text only, max 5,000 characters — but 1,600 when the channel includes SMS, so keep it short if sending by SMS. Rate limits (200 per API key per 24h, 3 per recipient per 24h) and the account suppression list are enforced server-side. Pass idempotency_key only if the user supplied one; do not invent one. Requires the Send Message module enabled on the account — on 403 "module not enabled", do NOT retry; tell the user to contact Sweeppea support. When a send is refused, call fetch_messaging_usage first: it is what distinguishes module access, plan channels, an exhausted allowance, a sending pause and a missing 10DLC number. Direct sending is a SEPARATE account switch from the module: fetch_messaging_usage can report ModuleEnabled true while DirectMessageEnabled is false, and this call then returns 403 "Direct messages through the API are not enabled for your account yet" (observed in production 2026-09-30). That is account configuration, not a bug — do NOT retry; tell the user to contact Sweeppea support.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
channelYesemail, sms or both. both sends on each channel the participant has a usable address for
confirmYesMust be true. Set it ONLY after the user explicitly approved THIS action in this conversation, having been told what it does and that it cannot be taken back: a real email and/or SMS with this exact text goes out to that participant and cannot be recalled. Never assume, never carry an approval over from a previous item, never set it to satisfy the schema.
messageYesPlain text. Max 5,000 characters — max 1,600 when the channel includes SMS
subjectNoEmail subject, max 200 characters. Line breaks are collapsed. Defaults to a generic subject
idempotency_keyNoOptional, 8 to 64 characters [A-Za-z0-9_-]. Retrying with the same key never sends twice. Only pass one the user supplied
participant_tokenYesThe participant token (UUID v4) of a participant (regular or AMOE) of your account

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.2/5.0
Behavior3/5

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

The description goes well beyond the annotations: irreversibility ('cannot be recalled'), rate limits (200/24h, 3/recipient/24h), suppression list, the Send Message module requirement, the separate DirectMessageEnabled switch, and non-retry guidance on 403s. That said, destructiveHint=false is declared while the operation is irreversible and leaves the platform, a nuance an agent must reconcile. Rich context, but the safety-profile tension keeps it below the top.

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-loads the critical warning ('SENDS A REAL MESSAGE... cannot be recalled') before operational details, which is exactly right for a destructive action. It is long and the trailing 403/account-switch detail is dense, but nearly every sentence carries operational value.

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 no output schema, the description compensates fully: it covers irreversibility, approval gating, channel limits, server-enforced rate limits and suppressions, prerequisite module configuration, and the precise error paths to follow. An agent has everything needed to call this safely.

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

Parameters3/5

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

Schema description coverage is 100% and the schema itself already documents channel, confirm, message length limits, subject defaulting, and idempotency_key semantics in detail. The description largely echoes this ('Plain text only, max 5,000... but 1,600 when SMS'), adding only marginal reinforcement, so baseline 3 applies.

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 ('Queue ONE email and/or SMS') plus the scope constraint ('to one of your OWN participants'). This clearly distinguishes it from sibling senders like send_code and send_file, which message using platform-generated content rather than agent-written text.

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 when to use it, when NOT (no address field, cannot message anyone else), the confirm=true prerequisite tied to user approval, and the alternative tool to call when a send is refused (fetch_messaging_usage). It also instructs the agent not to retry on specific 403s.

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

All Sweeppea MCP 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