Skip to main content
Glama

Messaging: Send to contact

messaging_send_to_contact
Destructive

One-step send for voice-style requests: 'send a WhatsApp to Julien saying I'm 10 minutes late'. Resolves the recipient like messaging_resolve_recipient and sends the text ONLY when exactly one person matches (existing conversation or contact). When lookup is incomplete or several people match, nothing is sent and the candidates are returned so you can ask the user which one. The user must have stated the message content; do not invent it.

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": {
      "provider": "<provider>",
      "name": "<name>",
      "text": "<text>"
    },
    "name": "messaging_send_to_contact"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesHow the user refers to the recipient.
textYesExact message text the user asked to send.
inbox_idNoRequired for Facebook: exact personal or PAGE_<id>_INBOX inbox.id from facebook_list_inboxes. Preserves the sending identity. Omit for other providers.
providerYesMessaging provider named by the user. LinkedIn recipients use linkedin_resolve_person + linkedin_start_conversation instead.
account_idNoOptional Nilyo connection ID (unipile_account_id from list_connected_accounts). Required when the user has several accounts for the provider: pick the one the user named.
recipient_user_idNoExact provider user ID chosen by the user after an ambiguous result; skips name matching.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / inbox_id
      Added value: +{
      +  "description": "Required for Facebook: exact personal or PAGE_<id>_INBOX inbox.id from facebook_list_inboxes. Preserves the sending identity. Omit for other providers.",
      +  "minLength": 1,
      +  "type": "string"
      +}
    • changedInput schema / properties / provider / enum
      Previous value: -[
      -  "whatsapp",
      -  "instagram",
      -  "telegram"
      -]New value: +[
      +  "whatsapp",
      +  "instagram",
      +  "facebook",
      +  "telegram"
      +]
  2. First observed

TDQS

A4/5.0
Behavior4/5

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

The annotations already declare a write (readOnlyHint=false, destructiveHint=true, idempotentHint=false, openWorldHint=true), so the bar is lower, and the description still adds real value: it discloses the single-match guard that prevents accidental sends and the candidate-return behavior on ambiguity. It does not explain what a successful send returns or whether retries could duplicate a message, which matters given idempotentHint=false.

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?

Four sentences, all load-bearing, front-loaded with the capability and followed by the guard conditions and the anti-invention rule. The quoted user example is compact and doubles as a usage cue. Slightly longer than strictly necessary, but nothing is filler.

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?

Covers the decision an agent must make (send now vs. surface candidates) plus the content-integrity rule, which is the main risk for a write tool of this shape. With a fully documented schema and annotations carrying the safety profile, and no output schema to explain, this is close to complete. The only gap is post-send behavior/return values.

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% with rich per-parameter descriptions, so the baseline is 3. The description goes beyond that by describing the name-matching semantics (must resolve to exactly one person) and by setting up the ambiguous-result flow that explains what recipient_user_id is for. It adds no detail on provider, account_id, or inbox_id, but the schema already covers those thoroughly.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a concrete verb+resource ("One-step send" of a text to a resolved contact) and anchors it to a realistic user utterance. It references the sibling messaging_resolve_recipient as the lookup it performs, which separates it from a two-step resolve-then-send flow. It never contrasts itself with messaging_send_message or provider-specific senders like whatsapp_send_message, so sibling differentiation is only partial.

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 a clear trigger ("voice-style requests" with the content already stated) and an explicit when-not: if lookup is incomplete or multiple people match, nothing is sent and candidates come back to ask the user. It adds a hard prohibition against inventing the message text. What's missing is explicit routing to an alternative tool when the agent is unsure or wants a preview, which is what a 5 would require.

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.