Skip to main content
Glama
Postmark Account MCP

Postmark Account MCP

by ckaklamanos

Message delivery timeline

get_message_details
Read-onlyIdempotent

Retrieve full details and event timeline for one outbound Postmark message, including delivery, bounce, open, and click events, with optional body content.

Instructions

Full details + event timeline (Delivered, Bounced, Opened, Clicked, ...) of one outbound message. If server is omitted, all servers are tried.

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": {
      "message_id": "<message_id>"
    },
    "name": "get_message_details"
  }
}

Input Schema

NameRequiredDescriptionDefault
serverNoServer name (partial, case-insensitive), numeric ID, or "account/server". Omit for ALL servers.
accountNoAccount name from the accounts file (partial, case-insensitive). Omit for ALL accounts.
message_idYesPostmark MessageID
include_bodyNoInclude text/html body (default false)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful behavior beyond that: the response includes an event timeline with named event types, and omitting server fans out across all servers. It says nothing about cost of include_body, rate limits, or what happens when the message is not found on the first server tried.

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?

Two short sentences, front-loaded with what the tool returns, which is the right priority. The second sentence duplicates information already in the server parameter description, so it is slightly redundant rather than wasteful. No filler or hedging.

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?

With no output schema, the description correctly compensates by naming the returned detail set and event types, which is the most important missing piece. However, for a 4-parameter read tool spanning accounts and servers, it omits how message_id interacts with the server/account filters (is the ID globally unique or per-server?) and gives no sense of response size or limits. Adequate but with clear gaps.

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%, so every parameter is already documented in the schema, making 3 the baseline. The description's server-omission note largely restates the schema's 'Omit for ALL servers', and it adds no meaning for message_id, account, or include_body. No compensation is needed, but no value is added either.

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 specific resource and scope: full details plus an enumerated event timeline (Delivered, Bounced, Opened, Clicked) for exactly one outbound message. An agent can distinguish it from search_messages or delivery_stats because it is singular and detail-oriented. It stops short of naming a sibling to contrast with, so it is clear but not maximally differentiated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The only conditional statement is about parameter fallback ('If server is omitted, all servers are tried'), not about when to choose this tool over delivery_stats or search_messages. There is no statement of prerequisites (e.g., that a Postmark MessageID must already be known) or exclusions. Usage must be inferred from the parameter set.

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