Skip to main content
Glama

Assess Visual Symptoms & Urgent Red Flags (Educational)

assess_visual_symptoms
Read-onlyIdempotent

Evaluates a combination of visual symptoms against ArkSight's 26-condition optical pattern-matching engine, checks for urgent ophthalmic/neurological red-flag warnings (such as retinal detachment curtains, sudden flashes + floaters, or hemifield stroke loss), and generates a link to a 2-page printable clinic summary PDF the user can bring to an optometrist or ophthalmologist. Educational only, never a diagnosis.

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": "assess_visual_symptoms"
  }
}

Input Schema

NameRequiredDescriptionDefault
blurFarNoDistance blur on the background mountains while foreground dog stays sharp (0 to 10; myopia).
blurNearNoNear-field blur on the foreground dog while distant mountains stay clear (0 to 10; hyperopia/presbyopia).
floatersNoDrifting dark specks, cobwebs, and rings % (0 to 100; PVD, retinal detachment, diabetic retinopathy, uveitis).
brightnessNoOverall light brightness % (100 = normal, lower = night blindness or optic dimming).
cloudyHazeNoCloudy, milky lens or corneal haze washing out contrast % (0 to 100; cataracts, uveitis, Fuchs', keratitis).
glareHalosNoLuminous halos and starburst glare around the streetlamp % (0 to 100).
visualSnowNoFine grainy TV-like static across the visual field % (0 to 100; visual snow syndrome).
blurOverallNoOverall blur across near, mid, and far distances (0 to 10).
floaterSizeNoFloater size modifier when floaters > 0 (1 to 20, default 10).
kidFriendlyNoSet true for child-friendly wording on simulator deep-links.
doubleVisionNoGhosting / overlapping double vision intensity % (0 to 100; diplopia, keratoconus, astigmatism).
lightFlashesNoPeripheral arcs or flickers of light / photopsia % (0 to 100; PVD, retinal tear/detachment, ocular migraine).
tunnelVisionNoConcentric peripheral narrowing / tunnel vision % (0 to 100; glaucoma, retinitis pigmentosa).
curtainShadowNoDark curtain sweeping across vision % (0 to 100; urgent retinal detachment warning sign).
wavyDistortionNoMetamorphopsia wavy distortion bending straight lines like the streetlamp pole (0 to 50; AMD, macular pucker/hole, CSCR).
centralDarkSpotNoCentral scotoma / dark smudge at the center of gaze % (0 to 100; AMD, macular hole, Stargardt, optic neuritis).
missingPatchesGridNo16-character row-major 4x4 bitmask of missing field patches ('1' = blind patch, '0' = clear; e.g. '0011001100110011' for right hemianopia).

Output Schema

NameRequiredDescriptionDefault
matchesYes
disclaimerYes
clinicPdfUrlYes
simulatorUrlYes
urgentWarningsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • removedInput schema / properties / affectedEye
      Removed value: -{
      -  "description": "Which eye is affected ('both', 'left', or 'right').",
      -  "enum": [
      -    "both",
      -    "left",
      -    "right"
      -  ],
      -  "type": "string"
      -}
  2. Changed2 schema fields changed
    • addedInput schema / properties / affectedEye
      Added value: +{
      +  "description": "Which eye is affected ('both', 'left', or 'right').",
      +  "enum": [
      +    "both",
      +    "left",
      +    "right"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / kidFriendly
      Added value: +{
      +  "description": "Set true for child-friendly wording on simulator deep-links.",
      +  "type": "boolean"
      +}
  3. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds genuinely non-obvious behavior beyond that: it performs urgent red-flag detection (retinal detachment curtain, flashes + floaters, hemifield loss) and produces a PDF link as a side artifact, plus an explicit not-a-diagnosis disclaimer. It stops short of saying how red flags are surfaced in the response, but that is partly covered by the output schema.

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?

A single sentence, but well front-loaded: core action first, red-flag checks second, PDF artifact third, disclaimer last. The parenthetical red-flag examples are justified because they define what counts as urgent. Slightly dense but no sentence is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 17-parameter, all-optional assessment tool with a full schema, complete annotations, and an output schema, the description covers purpose, red-flag behavior, the returned PDF artifact, and the diagnostic disclaimer. Nothing essential to correct invocation is missing.

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% with 17 richly documented parameters, including clinical interpretations and valid ranges such as the 16-character bitmask pattern. The description adds no parameter-level meaning whatsoever, so the schema does all the work and the baseline of 3 applies.

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 names a specific verb (evaluates), the resource (a combination of visual symptoms), the underlying mechanism (ArkSight's 26-condition optical pattern-matching engine), and two concrete side effects: red-flag warnings and a printable clinic summary PDF. It is clearly distinguishable from siblings like simulate_vision and list_eye_conditions, which do rendering and cataloging rather than assessment.

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 context is implied rather than stated: the tool is positioned as an educational screening step whose output is brought to an optometrist or ophthalmologist. The 'Educational only, never a diagnosis' clause constrains scope, but there is no explicit when-to-use-this-vs-simulate_vision guidance or any statement about prerequisites, though the implied workflow is inferable.

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.