Skip to main content
Glama
Sign In

Sendocado

by com.sendocado
OverviewDiscussionsAdmin

Test sender credentials

check_sender
Read-only

Test provider credentials with the provider without saving anything, before update_sender. A null credential tests the one stored for the same provider. Answers is_ok, or the provider's reason.

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>",
      "from_name": "<from_name>",
      "from_email": "<from_email>",
      "reply_to_email": "<reply_to_email>",
      "max_sends_per_hour": "<max_sends_per_hour>",
      "provider": "<provider>"
    },
    "name": "check_sender"
  }
}

Input Schema

NameRequiredDescriptionDefault
providerYesThe provider account and its credentials. A null credential keeps the one stored for the same provider. Gmail is first connected in the app.
from_nameYesThe name people see the email from, e.g. "Maya at Acme".
from_emailYesAn address on a domain the provider has verified.
project_idYes
reply_to_emailYesReply-To for transactional email; marketing replies come to Sendocado.
max_sends_per_hourYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true; the description adds real context beyond them — that nothing is persisted, that a null credential falls back to stored credentials for the same provider, and that the response is either an is_ok or the provider's failure reason. It does not mention latency, rate limits, or side effects on the remote provider's API (calls do hit an external service), which would round it out.

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?

Two short sentences, front-loaded with the action and its non-persisting constraint, then the null-credential behavior and return shape. No filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The provider oneOf is complex and the description handles the credential-null case well, but it leaves unexplained why the non-credential sender fields are mandatory for a test, and there is no output schema to fall back on for the is_ok/reason shape beyond one clause.

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?

At 67% schema coverage the schema already documents provider, from_name, reply_to_email and the null-credential semantics, which the description largely echoes. The description does not explain why from_email, from_name, reply_to_email and max_sends_per_hour are required for a credential test — a real semantic gap for four of six required params.

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 ("Test provider credentials with the provider") plus the key constraint ("without saving anything") and explicitly contrasts with update_sender. An agent can distinguish this dry-run tool from the mutating siblings without opening a 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?

Gives clear usage context: run this before update_sender, and pass a null credential to test the already-stored one rather than re-entering secrets. It stops short of stating exclusions (e.g., when to skip the test entirely), so it is not a full when/when-not statement.

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

All Sendocado 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