Skip to main content
Glama

send16-mcp

by io.github.spruikco
OverviewDiscussionsAdmin

Import contacts

import_contacts
Destructive

Bulk import contacts from CSV data (min column: email), optionally straight into audiences and/or with tags. This is the tool for cross-app flows; e.g. pulling people out of Gmail, a CRM, or a spreadsheet and landing them in a Send16 audience in one call. Set updateExisting for upsert semantics (safe to re-run). Requires consentConfirmed: true, so confirm with the user that everyone on the list opted in before calling.

Input Schema

NameRequiredDescriptionDefault
tagsNoTag NAMES to apply to all imported contacts; matched case-insensitively, created if missing
apiKeyNoSend16 API key (overrides SEND16_API_KEY env var)
csvDataYesCSV string with headers. Required column: "email". Optional: "firstName", "lastName"
audienceIdsNoAdd all imported contacts to these audience IDs (see list_audiences / create_audience)
updateExistingNoWhether to update contacts that already exist
consentConfirmedNoRequired, must be true. Set it only after the user has confirmed every person on this list opted in to hear from them. Never set it for bought, rented or scraped lists. If you haven't asked, ask first.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / tags / description
      Previous value: -"Tag NAMES to apply to all imported contacts — matched case-insensitively, created if missing"New value: +"Tag NAMES to apply to all imported contacts; matched case-insensitively, created if missing"
  2. Changed1 schema field changed
    • addedInput schema / properties / consentConfirmed
      Added value: +{
+  "description": "Required, must be true. Set it only after the user has confirmed every person on this list opted in to hear from them. Never set it for bought, rented or scraped lists. If you haven't asked, ask first.",
+  "type": "boolean"
+}
  3. Changed3 schema fields changed
    • addedInput schema / properties / audienceIds
      Added value: +{
+  "description": "Add all imported contacts to these audience IDs (see list_audiences / create_audience)",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}
    • changedInput schema / properties / csvData / description
      Previous value: -"CSV string with headers. Required column: \"email\". Optional: \"firstName\", \"lastName\", \"tags\" (comma-separated within quotes)"New value: +"CSV string with headers. Required column: \"email\". Optional: \"firstName\", \"lastName\""
    • changedInput schema / properties / tags / description
      Previous value: -"Tag names to apply to all imported contacts"New value: +"Tag NAMES to apply to all imported contacts — matched case-insensitively, created if missing"
  4. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations give the safety profile (destructiveHint=true, idempotentHint=false), and the description adds non-obvious behavior: updateExisting delivers upsert semantics that make re-runs safe, tags are created if missing, and a consent gate is enforced. Note the mild tension with idempotentHint=false — the re-run safety is conditional on setting updateExisting=true, which the description could have stated more sharply, but it is not a contradiction of the default behavior.

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?

Three dense sentences, front-loaded with the core action and required column, then usage context, then the consent gate. No filler and every sentence carries distinct information.

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 6-param mutation tool with no output schema, the description covers the action, the input format, the upsert option, and the consent precondition well. It does not indicate what the call returns (e.g., counts of imported/skipped/failed rows), which would be the remaining gap given no output schema exists.

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 coverage is 100% and each parameter already carries a rich description, so the baseline is 3. The description adds only marginal framing on top of that ('upsert semantics (safe to re-run)' for updateExisting, the opt-in rationale for consentConfirmed), which reinforces rather than extends the schema.

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?

Specific verb + resource + input format: 'Bulk import contacts from CSV data (min column: email)'. It further scopes itself as 'the tool for cross-app flows', which separates it from single-record siblings like create_contact and audience-scoped add_contacts_to_audience.

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 concrete usage context (pulling people from Gmail, a CRM, or a spreadsheet into a Send16 audience) and a hard precondition (consentConfirmed must be true, confirm opt-in first). It doesn't explicitly say when to prefer create_contact or add_contacts_to_audience instead, so it stops short of full when/when-not routing.

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

All send16-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