The Comp Desk Builder

NY maximum and minimum weekly benefit

get_max_min_rate

Read-onlyIdempotent

The New York maximum and minimum weekly workers' compensation benefit for a date of accident (the rate year runs July 1 to June 30; the maximum is fixed by the date of accident, never by today's date). Use for "what is the max rate for a 2025 injury". New York State only. Computes with The Comp Desk calc-core (the engine behind the app, the website calculators and the Pro Workspace); it never estimates. If an input is missing it returns status "missing" with every input still needed and calculates nothing. Returns the figures, the rate year used, the formulas with their citations (each flagged with whether it has been attorney-reviewed), 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": {
      "date_of_accident": "<date_of_accident>"
    },
    "name": "get_max_min_rate"
  }
}

Input Schema

Name	Required	Description	Default
`date_of_accident`	Yes	Date of accident (injury), YYYY-MM-DD. Only a full date the user gave; never a guessed one.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 13, 2026

TDQS

A4.2/5.0

Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, and the description adds substantial context on top: it never estimates, it returns status "missing" with the full list of needed inputs and computes nothing, it requires a builder key, and it discloses the return payload (figures, rate year, cited formulas with attorney-review flags, not-legal-advice notice). That is well beyond what the annotations provide.

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 critical facts (NY-only, rate year, missing-input behavior) are front-loaded in a single dense paragraph. However, the calc-core engine is described twice ("the engine behind the app, the website calculators and the Pro Workspace" and "Same engine the Pro Workspace tiles call through CD.Calc"), and "matches the app to the cent" is promotional filler that could be cut.

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?

With no output schema, the description carries the return-value burden and does so fully: figures, rate year, formulas with citations and review flags, and the disclaimer. It also covers failure behavior and auth requirements, leaving nothing an agent needs to call it correctly.

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?

Schema coverage is 100%, so the baseline is 3, but the description adds real semantic weight: the maximum is fixed by the date of accident and never by today's date, which tells the agent how to interpret and populate the parameter. The schema's own "never a guessed one" note overlaps somewhat but the rate-year rule is genuinely additive.

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

Purpose4/5

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

States a specific resource (NY maximum and minimum weekly workers' comp benefit) with a precise scope qualifier (rate year July 1–June 30, fixed by date of accident). It is clearly distinguishable from the calculate_* siblings by being a lookup of published state figures rather than a computation, though it never names an alternative tool to reinforce that contrast.

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?

Gives a concrete trigger phrase ("what is the max rate for a 2025 injury") and a hard exclusion ("New York State only"). It does not explicitly say when to prefer a sibling such as calculate_weekly_rate, so the routing guidance stops just short of fully explicit.

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?