Nova

Blood pressure readings

get_vitals

Read-onlyIdempotent

Retrieve recent vital readings, averages, and doctor-set limits to track blood pressure trends and answer care questions over a chosen period.

Instructions

'What's Mom's blood pressure?', 'How has my blood pressure been?' Recent readings, the average and the doctor's limits.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_vitals"
  }
}

Input Schema

Name	Required	Description	Default
`days`	No	How far back

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 24, 2026

TDQS

B3.1/5.0

Behavior3/5

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

The annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile needs no restating. The description adds that results include an average and the doctor's configured limits, which is useful scope information, but says nothing about behavior such as handling of missing readings or the effect of the default window.

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?

It is a single short sentence with negligible waste and leads with the most recognizable framing (the user's actual question). The nested-quote phrasing is slightly awkward, which keeps it from a 5, but nothing needs to be cut.

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 an output schema present, the description need not explain return shape, and the annotations plus fully documented single parameter cover the mechanics. Still, for a health-data read tool it omits the tool's scope limits (only blood pressure? all vitals?) and any note on empty results, which an agent would want before calling.

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 description coverage is 100% — the single 'days' parameter documents 'How far back' with default 7 and a 1-60 range. The description's 'Recent readings' only loosely gestures at the time window and adds no syntax or default behavior beyond the schema, so the baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The example questions ('What's Mom's blood pressure?') plus 'Recent readings, the average and the doctor's limits' convey that this retrieves blood pressure history and summary thresholds, but there is no explicit verb+resource statement. The name says 'vitals' while the title and body narrow to blood pressure, leaving the scope slightly ambiguous against the sibling log_vitals, which is never named.

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 only implied through the quoted caregiver questions, which do sketch the situations where this tool applies (checking a recent reading or a trend). There is no explicit when-to-use, no statement of when not to use it, and no pointer to log_vitals for recording versus reading.

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