Skip to main content
Glama
Sign In

MedDroid

by io.github.sanjaydoc
OverviewDiscussionsAdmin

Explain a lab result

explain_lab_result
Read-onlyIdempotent

Explains one lab test value in plain words (for example HbA1c 6.1 %, TSH 6.2, platelets 90,000, creatinine 1.4): the usual normal range, what this value usually means, and when to see a clinician. General information from MedDroid, not a diagnosis.

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": {
      "test": "<test>",
      "value": "<value>"
    },
    "name": "explain_lab_result"
  }
}

Input Schema

NameRequiredDescriptionDefault
ageNo
sexNo
testYesTest name, e.g. HbA1c, TSH, platelet count
unitNo
valueYesThe result, e.g. 6.1
languageNoReply language, e.g. English, Hindi, Tamil

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

The annotations already establish that this is a read-only, idempotent, non-destructive, closed-world operation. The description adds useful behavioral context by saying it returns the usual normal range, an interpretation, and clinician guidance, and by explicitly framing the output as general information rather than a diagnosis.

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?

The description is front-loaded with the core action and remains a single compact sentence. The parenthetical examples are useful, though they make the sentence dense and could have been separated for readability.

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 six-parameter informational tool with no output schema, the description does well by explaining the conceptual return content and adding a clear non-diagnosis disclaimer. It is slightly incomplete because it does not clarify how optional parameters like age, sex, or language affect the explanation.

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 50%: test and value are documented, while age, sex, unit, and language are not described in the schema. The description helps by giving example values such as 'HbA1c 6.1 %' and 'platelets 90,000', which clarify expected formats, but it does not explain the optional demographic, unit, or language parameters.

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 and resource: 'Explains one lab test value in plain words.' The phrase 'one lab test value' also scopes it away from a full lab report, and the examples make the intended unit of work concrete.

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 by the single-value scope and examples, but there is no explicit guidance on when to use this versus explain_lab_report or other sibling tools. The 'when to see a clinician' phrase describes output content rather than when to invoke the tool.

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

All MedDroid 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