Sendocado

Send test email

send_test_email

Send a test of an email to the user's own inbox, so they see the real thing before anyone else gets it. Merge tags use contact_id's values when it is set. Test emails are never tracked and have a tighter rate limit. Send it only to an address the user gave you as theirs.

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": {
      "project_id": "<project_id>",
      "to": "<to>",
      "subject": "<subject>",
      "preview_text": "<preview_text>",
      "html": "<html>",
      "markdown": "<markdown>",
      "template_id": "<template_id>",
      "contact_id": "<contact_id>"
    },
    "name": "send_test_email"
  }
}

Input Schema

Name	Required	Description
`to`	Yes	The user's own address.
`html`	Yes	The body as HTML. Null when you send markdown or a template_id.
`subject`	Yes
`markdown`	Yes	The body as markdown. Null when you send html or a template_id.
`contact_id`	Yes	Fill merge tags from this contact; null leaves them as their fallbacks.
`project_id`	Yes
`template_id`	Yes	Copy a template's subject, preview text and body; then subject, preview_text, html and markdown are null.
`preview_text`	Yes	The line inbox previews show after the subject.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 5, 2026

TDQS

A4.1/5.0

Behavior5/5

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

Beyond the annotations (which only say non-readonly, non-destructive, non-idempotent, open-world), the description discloses two behavioral facts the agent could not otherwise know: test emails are never tracked and the endpoint has a tighter rate limit. It also explains merge-tag resolution via contact_id. These are exactly the operational caveats that matter for a send operation.

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 short sentences, front-loaded with purpose and ending on the safety constraint, with no filler. Minor redundancy exists where the contact_id merge-tag behavior restates the schema's own wording.

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 an 8-required-parameter mutation with no output schema, the description covers the important non-obvious ground: recipient restriction, rate limit, tracking behavior, and merge-tag resolution. It does not explain what the call returns or how project_id and template_id selection interact, though the schema partially covers the latter.

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 75%, so the schema documents most parameters including the template_id vs html/markdown exclusivity. The description repeats the contact_id merge-tag semantics already in the schema and reinforces that "to" must be the user's own address, but says nothing about project_id or the interaction between template_id and the body fields. Baseline 3 is appropriate.

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?

The description uses a specific verb and resource ("Send a test of an email") and scopes the recipient to "the user's own inbox," which separates it from real sends like send_transactional_email or create_broadcast. It stops short of naming any sibling tool explicitly, leaving the agent to infer the distinction from wording alone.

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?

"Send it only to an address the user gave you as theirs" is a hard gating rule that tells the agent exactly when this tool is appropriate and prevents misuse with arbitrary recipients. The stated rationale ("so they see the real thing before anyone else gets it") clarifies intent, but no alternative is named for non-test sends.

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

All Sendocado tools Inspect

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

Need Help?