Skip to main content
Glama

判讀居家血壓

health__check_home_blood_pressure
Read-onlyIdempotent

[台灣健康資訊]判讀居家血壓(依台灣 2022 高血壓指引 130/80),回傳平均、分級、是否達危急值與 722 量測方法。readings 例:128/82,134/86(最多 6 筆)。

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": {
      "readings": "<readings>"
    },
    "name": "health__check_home_blood_pressure"
  }
}

Input Schema

NameRequiredDescriptionDefault
readingsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

The annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so safety is covered. The description adds value beyond that: it discloses the return payload (average, classification, critical-value flag, 722 measurement method) and the domain rule base (2022 Taiwan guideline, 130/80), so the agent knows what a call yields. It does not state error behavior for malformed readings, which keeps it from a 5.

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 compact clauses: the first front-loads purpose, standard, and return contents; the second gives the input format and its limit. There is no redundant restatement of the title or annotations, and every phrase carries 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 single-parameter, annotation-covered, output-schema-less tool, the definition covers what is computed, against which guideline, what comes back, and how to format input. The only gap is that the '722 量測方法' payload is referenced but not glossed, and no failure mode is described.

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 description coverage is 0% and the single readings parameter is a bare string, so the description must carry the format — and it does, with '例:128/82,134/86' showing comma-separated systolic/diastolic pairs and '(最多 6 筆)' capping the count at six. Separator tolerance and invalid-input handling remain unspecified.

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?

The description uses a specific verb, 判讀 (interpret), and a specific resource, 居家血壓 (home blood pressure), and it sets the interpretive standard (台灣 2022 高血壓指引 130/80). This clearly distinguishes it from sibling checks such as health__check_blood_glucose or wellness__check_telehealth_eligibility without requiring the agent to open 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 Guidelines3/5

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

Usage is implied — the tool is used when the user has home BP readings to interpret — and the input example shows the expected call shape. However, the description states no explicit when-to-use or when-not-to-use conditions and names no alternative tool for related cases such as single office readings or other vitals.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources