The Comp Desk Builder

NY radiculopathy severity rank

rank_radiculopathy

Read-onlyIdempotent

The cervical or lumbar radiculopathy severity ranking, scored the way the Pro Workspace Radiculopathy tile scores it, from the 2012 NYS Impairment Guidelines tables as calc-core carries them: imaging 16, EMG 6, muscle weakness by grade (0–1: 20, 2: 18, 3: 6, 4–5: 0) plus atrophy 6 under the root's weakness cap, sensory (compromised 4, anesthesia 6) under the root's sensory cap, reflex (diminished 4, absent 6), tension signs 4; the letter from Table S11.7. Give the findings (unlisted findings count as normal / no), or instead total_points to rank a total already scored. A total with no row on Table S11.7 (1–3 points, or above the top row) is refused with the reason, never given a letter. Cervical roots C5–T1, lumbar L3–S1. New York State only. Computes with The Comp Desk calc-core, the same engine as the app and the Pro Workspace; it never estimates. A missing input returns status "missing" and nothing is calculated. Returns the figures, the steps with the rule and engine function behind each, and the not-legal-advice notice. Needs your builder key. Same engine the Pro Workspace tiles call through CD.Calc, so a figure here matches the app to the cent.

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": {
      "region": "<region>"
    },
    "name": "rank_radiculopathy"
  }
}

Input Schema

Name	Required	Description
`emg`	No	EMG fibrillations / positive sharp waves in 2+ muscles of the root.
`reflex`	No
`region`	Yes
`imaging`	No	Imaging shows nerve-root displacement or encroachment that correlates.
`sensory`	No
`nerve_root`	No
`total_points`	No	Instead of the findings: a total already scored, to rank.
`tension_signs`	No	Spurling's, straight leg raise or femoral stretch positive.
`muscle_atrophy`	No
`muscle_weakness_grade`	No	Motor grade 0–5; default 5 (normal).

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 13, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Beyond the readOnly/idempotent annotations, it discloses the auth requirement (builder key), the failure mode for missing inputs (status "missing", nothing calculated), the refusal path for unrankable totals, the determinism claim (never estimates), and the return contents (figures, per-step rule and engine function, not-legal-advice notice). That is a rich behavioral profile an agent cannot get from the annotations.

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?

The purpose is front-loaded, but the body is one long semicolon-and-colon run-on. The engine-equivalence claim is made three separate times ("scored the way the Pro Workspace Radiculopathy tile scores it", "Computes with The Comp Desk calc-core", "Same engine the Pro Workspace tiles call through CD.Calc"), which is redundant and crowds out other detail.

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 no output schema, the description steps in to describe the return payload (figures, steps, notice) and covers the refusal and missing-input paths, which is what an agent needs to call it safely. The only soft spot is that it never clarifies whether nerve_root is expected when total_points is used, leaving a small ambiguity for a 10-parameter tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With only 50% schema description coverage across 10 parameters, the description carries real weight: it supplies the point values for imaging (16), EMG (6), each weakness grade, atrophy (6), sensory states, reflex states, and tension signs (4), plus the cap semantics for weakness and sensory. It does not elaborate region or nerve_root beyond their enums, but those are self-explanatory, so the compensation is largely complete.

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 computation (cervical/lumbar radiculopathy severity ranking under the 2012 NYS Impairment Guidelines, Table S11.7) and fully bounds its scope: cervical roots C5–T1, lumbar L3–S1, New York State only. An agent can tell immediately this is the radiculopathy scorer and not one of the many other calculate_* siblings.

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

Usage Guidelines4/5

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

It gives clear mode selection: supply the findings (with unlisted findings defaulting to normal/no), or supply total_points to rank an already-scored total. It also states the exclusion condition — totals with no row on Table S11.7 (1–3 points or above the top row) are refused — which is real when-not guidance, though nothing directs the agent to a sibling tool for adjacent body parts or other state jurisdictions.

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

All The Comp Desk Builder tools Inspect

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

Need Help?