EveryCalc

calculate_tsp

Read-onlyIdempotent

Projected TSP balance with annual employee contributions (capped at the 24,500 USD elective deferral limit used by the page) plus, when matching is on, the BRS agency contribution: 1 percent automatic plus a match of 100 percent of the first 3 percent of pay and 50 percent of the next 2 percent. Contributions are treated as annual amounts compounded with the starting balance, as on the page. The page's Roth percent field is not used by its calculation and is not a parameter here. Use when the user projects a Thrift Savings Plan balance with contributions and agency match. For a civilian 401k use calculate_401k. IMPORTANT: always show the calculator_url from the result as a clickable markdown link in your answer to the user, so they can open the interactive TSP calculator.

Input Schema

Name	Required	Description
`years`	Yes	Projection horizon in years.
`salary`	Yes	Annual salary (basic pay basis) in USD.
`balance`	No	Current TSP balance in USD.
`match_on`	No	Whether BRS agency automatic and matching contributions apply.
`return_pct`	Yes	Annual return percent.
`contrib_pct`	Yes	Employee contribution percent of salary.

Output Schema

Name	Required	Description
`ok`	Yes	True when the calculation succeeded.
`note`	Yes	Disclaimer that accompanies every result.
`tool`	Yes	Name of the tool that ran.
`inputs`	No	The normalized inputs the calculation used.
`results`	Yes	The computed figures for this calculator.
`calculator_url`	Yes	Deep link to the matching interactive calculator on everycalc.xyz.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 21, 2026

addedOutput schema / properties / note

Added value: +{
+  "description": "Disclaimer that accompanies every result.",
+  "type": "string"
+}

changedOutput schema / required

Previous value: -[
-  "ok",
-  "tool",
-  "results",
-  "calculator_url"
-]New value: +[
+  "ok",
+  "tool",
+  "results",
+  "calculator_url",
+  "note"
+]

Changed1 schema field changedOct 17, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "calculator_url": {
+      "description": "Deep link to the matching interactive calculator on everycalc.xyz.",
+      "type": "string"
+    },
+    "inputs": {
+      "description": "The normalized inputs the calculation used.",
+      "type": "object"
+    },
+    "ok": {
+      "description": "True when the calculation succeeded.",
+      "type": "boolean"
+    },
+    "results": {
+      "description": "The computed figures for this calculator.",
+      "type": "object"
+    },
+    "tool": {
+      "description": "Name of the tool that ran.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "ok",
+    "tool",
+    "results",
+    "calculator_url"
+  ],
+  "type": "object"
+}

First observedOct 15, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), but the description goes further by disclosing the actual computation model: annual contributions compounded with starting balance, the 24,500 USD elective deferral cap, and the exact BRS match formula (1% automatic + 100% of first 3% + 50% of next 2%). It also notes the Roth percent field is deliberately excluded. This shapes how an agent interprets results, though it doesn't cover error modes or defaults.

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?

Dense and mostly value-bearing, but the opening sentence is a long run-on formula dump and the actual purpose/usage statement is deferred to the middle. A leading purpose sentence followed by the match rules would front-load better; the trailing IMPORTANT formatting directive is justified but tacked on.

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?

Given an output schema exists (so return shape needn't be explained), the description still supplies everything needed to call and interpret the tool: contribution cap, match rules, compounding basis, and the requirement to surface calculator_url to the user. Nothing material is missing for a 6-parameter read-only calculator.

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 meaning: contrib_pct is bounded by the elective deferral cap, salary is on a basic-pay basis, match_on triggers the stated agency formula, and the page's Roth percent parameter is explicitly excluded. This is more than restating the schema.

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?

States a specific verb+resource (projected TSP balance with contributions and agency match) and explicitly contrasts itself with the closest sibling, calculate_401k. An agent can distinguish it from all 60+ calculate_* siblings without opening the schema.

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

Usage Guidelines5/5

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

Explicit when-to-use clause ('Use when the user projects a Thrift Savings Plan balance with contributions and agency match') plus a named alternative for the divergent case ('For a civilian 401k use calculate_401k'). No inference required.

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

All EveryCalc 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.