Nova

Plan a refill (simulated pharmacy)

request_refill

Create a local refill handoff for the care circle without contacting a pharmacy; pharmacy and pickup timing are simulated. Leave medication empty to select the lowest-running one.

Instructions

Create a local refill handoff for the care circle. No request is sent to a pharmacy. The pharmacy and pickup timing are simulated. Empty medication means whatever is running lowest.

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": "request_refill"
  }
}

Input Schema

Name	Required	Description	Default
`medication`	No	Which medication; empty for the one running lowest

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 24, 2026

TDQS

A4/5.0

Behavior4/5

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

Beyond the annotations, the description discloses the key behavioral fact an agent needs: nothing leaves the system — no pharmacy request is sent and the pharmacy/pickup timing are simulated. That is exactly the kind of side-effect disclosure annotations cannot express. There is mild tension with openWorldHint=true, but that hint plausibly refers to the simulated pharmacy domain rather than a real external call, so it is not a genuine contradiction.

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?

Four short sentences, front-loaded with the action, then the negative scope, then the one parameter's default behavior. Every sentence adds information; nothing is redundant or bloated.

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?

With annotations, a fully covered single-parameter schema, and an output schema, the description covers what an agent needs: side effects, simulation, and the empty-parameter default. Only the care-circle handoff mechanics (who receives it, whether a confirmation is needed) are left implicit, which is a minor gap for a one-parameter tool.

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?

The schema has 100% description coverage and already states 'empty for the one running lowest'; the description repeats that same rule ('Empty medication means whatever is running lowest') without adding format, validation, or matching semantics. Baseline 3 applies since the schema carries the parameter meaning.

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 states a specific verb and resource — 'Create a local refill handoff for the care circle' — and immediately qualifies scope with 'No request is sent to a pharmacy' and 'simulated'. No sibling tool (log_medication, check_medication) does refill planning, so an agent can distinguish this immediately.

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?

The description makes the simulated nature clear, which implicitly tells the agent when this is appropriate (care-circle planning, not real pharmacy ordering). However, it never names an alternative or states exclusions relative to siblings like check_medication or log_medication, leaving the agent to infer that relationship.

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