Skip to main content
Glama

insync_get_message

Destructive

Reads one full secure patient-portal message, including subject, date, body and attachments. Unread messages stay unopened unless you confirm marking them read.

Instructions

Read one secure message in full (subject, sent date, body as plain text or Markdown, attachment list). WARNING: opening an UNREAD message marks it read in the portal — the practice can see that, and it cannot be undone. An unread message is NOT opened unless allow_mark_read is true; without it the tool returns the message’s metadata and a note asking you to confirm with the user first. An already-read message is opened freely.

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": {
      "child_id": "<child_id>",
      "master_id": "<master_id>"
    },
    "name": "insync_get_message"
  }
}

Input Schema

NameRequiredDescriptionDefault
viewNoResponse shape: "compact" (default) drops fields the response already carries elsewhere; "full" returns every field this server understands. compact projects each record to the fields a caller acts on; "full" keeps every field this server understands. (No "raw": the record is assembled here, not passed through from one endpoint.)
formatNoHow the body reads: "text" (default; lines, numbered items and link targets kept) or "markdown" (also keeps bold, lists, tables and links with their text).
child_idYesTODOChildId of the message, from insync_list_messages.
master_idYesTODOMasterId of the message, from insync_list_messages.
allow_mark_readNoSet true ONLY after the user agrees to let an unread message be marked read. Default false.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.5.0
    • addedInput schema / properties / format
      Added value: +{
      +  "description": "How the body reads: \"text\" (default; lines, numbered items and link targets kept) or \"markdown\" (also keeps bold, lists, tables and links with their text).",
      +  "enum": [
      +    "text",
      +    "markdown"
      +  ],
      +  "type": "string"
      +}
  2. First observedv0.1.0

TDQS

A4.7/5.0
Behavior5/5

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

The annotations already flag destructive=true and readOnlyHint=false, and the description adds the concrete consequence: opening an unread message marks it read in the portal, the practice can see that, and it cannot be undone. It also discloses the fallback behavior (metadata plus a confirmation note) and that already-read messages open freely — exactly the context an agent needs before a destructive call.

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 sentences, front-loaded with the payload and immediately followed by the WARNING and the gating rule. Every sentence carries distinct information — return contents, irreversibility, and the conditional guard — with no filler.

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

Completeness5/5

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

For a destructive read tool with no output schema, the description covers return fields, the irreversible side effect, the consent gate, and the fallback path. An agent has everything needed to call it correctly and safely without further context.

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%, so the baseline is 3, but the description adds real meaning: it explains the downstream effect of allow_mark_read (metadata-only response plus a confirmation prompt) and how body output relates to the text/markdown format choice. It stops short of documenting view semantics, which is left entirely to 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?

States a specific verb and resource ("Read one secure message in full") and enumerates what comes back (subject, sent date, body, attachment list), which clearly separates it from the sibling list-style tool insync_list_messages. The singular scope and returned fields let an agent pick it without opening the 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 explicit conditional guidance for the risky path: an unread message is NOT opened unless allow_mark_read is true, and without it the tool returns metadata plus a note asking the agent to confirm with the user first. It does not name a sibling alternative, but the when-to-use / when-not logic is spelled out clearly.

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