Skip to main content
Glama

Send a message to app users

appUsersSendEmail

Send one plain-text message with a one-line subject from an owned app’s verified sending address to up to ten of its own people — the Email page’s own send. Each person gets their own copy, so nobody sees who else received one. Requires confirmed: true, representing the human’s agreement to these exact words; without the literal nothing is sent. A message the provider takes cannot be recalled, and Tofu keeps no copy of it. Without a domain of the app’s own that the email provider reports verified, the call is refused in Tofu’s general words, with nothing sent; the Email page shows what is missing, and nothing ever leaves from Tofu’s shared address. sent and failed count what really left; message is Tofu’s own sentence for the person. The hour’s allowance is the account’s own email budget; only messages the provider took spend it. Sending again after an answer Tofu could not read is a second copy nobody can recall: ask the recipients what arrived first.

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": {
      "projectId": "<projectId>",
      "to": "<to>",
      "subject": "<subject>",
      "text": "<text>",
      "confirmed": "<confirmed>"
    },
    "name": "appUsersSendEmail"
  }
}

Input Schema

NameRequiredDescriptionDefault
toYes
textYes
subjectYes
confirmedYes
projectIdYes

Output Schema

NameRequiredDescriptionDefault
sentYes
failedYes
messageYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the annotations (openWorldHint, idempotentHint=false) it discloses exactly what an agent needs: the message cannot be recalled, no copy is retained, a verified owned domain is mandatory or the call is refused with nothing sent, the hourly allowance is the account's email budget and only provider-accepted messages spend it. It even flags the duplicate-send hazard on ambiguous responses, which explains why the operation is non-idempotent.

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 core action and recipient scope are front-loaded in the first sentence, and nearly every following sentence adds a distinct operational fact (gate, irreversibility, domain requirement, budget, retry hazard). The dense em-dash prose and idiosyncratic phrasing ('Tofu's general words', 'the Email page shows what is missing') make it slower to parse than necessary.

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 non-idempotent, externally visible send with an output schema, the description covers preconditions (verified owned domain, confirmed gate), side effects (irreversible, no retained copy), quota behavior, and retry risk. The output fields are already declared in the output schema, yet the description still clarifies that `sent`/`failed` count only what actually left — nothing material 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?

With 0% schema description coverage the description must carry the meaning, and it does for most params: `to` is constrained to the app's own people with a max of ten and per-recipient copies, `subject` is one line, `text` must be plain text, and `confirmed` must be the literal true value representing a human's agreement. `projectId` is only implied by 'an owned app' and is never named, leaving one required parameter unaddressed.

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?

The description names a specific verb and resource ('Send one plain-text message ... from an owned app's verified sending address to up to ten of its own people') and pins down scope: recipients are the app's own users, capped at ten, each receiving a private copy. An agent can distinguish this from appAuthEmailStatus or appInvitesCreate 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?

It gives a clear selection cue ('the Email page's own send', recipients must be the app's own people, max ten) and states the hard gate that `confirmed: true` is required or nothing is sent. It also warns to ask recipients before retrying after an unreadable response. It never names an alternative tool for out-of-scope cases (e.g. inviting external people), which is the only gap.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources