Skip to main content
Glama

QOF 90% asset test

calc_90_percent_test
Read-onlyIdempotent

Averages the two semiannual testing dates and, if the fund falls short, computes the Form 8996 Part IV penalty month by month (pass month-end figures in monthly for an exact figure; otherwise testing-date figures are applied to each half-year and the result is flagged as an approximation) at an underpayment rate the caller supplies.

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": {
      "d2_qozp": "<d2_qozp>",
      "d2_total": "<d2_total>"
    },
    "name": "calc_90_percent_test"
  }
}

Input Schema

NameRequiredDescriptionDefault
monthsNoMonths the entity was a QOF this year, 1-12 (default 12)
d1_qozpNo
d2_qozpYes
monthlyNoOptional month-end figures for Form 8996 Part IV: [{total, qozp, rate_pct}]
d1_totalNo
d2_totalYes
single_dateNotrue if only the year-end test applies (first year under 6 months); otherwise d1_* are required
underpayment_rate_pctNoIRS underpayment rate for the period, percent

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile needs no restating. The description adds real behavioral context beyond them: it discloses the fallback path, that the fallback result is explicitly flagged as an approximation, and that the underpayment rate is caller-supplied rather than derived. It does not say what the response contains (penalty amount, pass/fail), which keeps it off a 5.

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?

It is a single sentence with two levels of nested parentheticals, which makes the conditional logic hard to parse on first read. The purpose is front-loaded, and every clause does carry information, so nothing should be cut — but the structure should have been broken into separate sentences or bullets.

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?

For an 8-parameter tool with no output schema and only 50% schema coverage, the description explains the computation flow and the exact-vs-approximate branch, which is the critical part. It never states what the tool returns (a pass/fail determination plus a penalty figure is only inferable) and leaves several parameters to bare schema names, so an agent still has gaps to close.

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 8 parameters, the description has to carry weight, and it does: it explains that d1_*/d2_* are the two semiannual testing dates that get averaged, what monthly entries contain and override, and that underpayment_rate_pct is an input the caller must supply. Undocumented in either place are the semantics of months and the distinction between the qozp and total figures, so it is not complete.

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?

The description names a specific computation: averaging two semiannual testing dates and, on failure, computing the Form 8996 Part IV penalty month by month. The resource (QOF 90% asset test / Form 8996 Part IV) is unambiguous and no sibling calc_* tool overlaps it. It falls short of a 5 only because the verb-and-resource statement is buried inside one very long sentence rather than stated cleanly up front.

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?

There is genuine guidance on which input path to take — supply monthly figures for an exact result, otherwise testing-date figures are applied per half-year and the output is flagged as an approximation — but that is parameter-level usage, not tool-selection guidance. Nothing tells the agent when this tool applies versus the other calc_* siblings, and prerequisites (e.g., that the caller must look up the IRS underpayment rate) are only implied.

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.

Resources