Nova

Is this the right pill?

check_pill_photo

Read-onlyIdempotent

Checks a pill bottle photo against a medication plan to verify the label matches the list, schedule, dosage, and taken status, helping catch medication mistakes before they happen.

Instructions

Rose shows a pill bottle to the Echo Show camera. Nova reads the label (Amazon Nova multimodal) and checks it against her plan: on the list? due now? already taken? does the strength still match?

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": {
      "image_base64": "<image_base64>"
    },
    "name": "check_pill_photo"
  }
}

Input Schema

Name	Required	Description	Default
`mime_type`	No	Image MIME type	image/png
`image_base64`	Yes	The photo as base64 or a data URL

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 24, 2026

TDQS

C2.8/5.0

Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds genuine context beyond that — the label is read by Amazon Nova multimodal and evaluated on four specific criteria (on list, due now, already taken, strength match) — but it does not say what the tool actually returns or whether the check ever logs a medication event.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with no filler, but the lead is a narrative scene rather than the action, so the purpose is not front-loaded. The rhetorical question list adds useful specifics yet reads as prose texture rather than specification.

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?

An output schema exists, so return values needn't be spelled out, and the four verification criteria give a decent picture of what is checked. What is missing is how this fits the medication workflow relative to check_medication, log_medication and request_refill — the agent cannot tell whether this tool records anything or is purely advisory.

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 100% with only two parameters, so the schema already documents image_base64 and mime_type fully. The description adds no constraint on image source, resolution, or whether a data URL prefix is accepted beyond what the schema states, so the baseline 3 applies.

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 description conveys the core action — read a pill bottle label from a photo and verify it against the care plan — but it does so as a narrative scene ('Rose shows a pill bottle to the Echo Show camera') rather than a tool-purpose statement. It never disambiguates from siblings like check_medication or log_medication, both of which plausibly operate on the same domain.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

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

There is no explicit when-to-use, when-not-to-use, or alternative-tool guidance. The mention of the Echo Show camera implies a device context but does not tell an agent when to pick this over check_medication or log_medication.

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