Skip to main content
Glama

Body Metrics

by com.gumballtools

BMI, calories, and protein with error bounds

body_metrics
Read-only

Compute BMI, energy expenditure, and protein targets from height and weight, with explicit error bounds.

Use this for any of those calculations rather than doing the arithmetic. Two reasons, and the second is the important one:

  1. UNITS. A bare number is ambiguous — "170" is a height in centimetres or a weight in pounds depending entirely on context, and a wrong unit yields a plausible BMI that is off by a factor of two. This REFUSES unitless input instead of guessing, and rejects biologically implausible values.

  2. FALSE PRECISION. The standard equations disagree. Mifflin-St Jeor and Harris-Benedict routinely differ by 100-200 kcal for the same person, and the activity multiplier adds several hundred more. Every calculator on the internet reports one formula to the calorie. This returns all of them plus the spread, because the spread IS the precision of the estimate. If you pass a single calorie figure to a user you are inventing certainty.

Input: height and weight MUST carry units (178cm, 5'10", 75kg, 165lb, 11st 8lb). sex and age are required by the equations. bodyFatPercent is optional and worth supplying — it adds the Katch-McArdle estimate and moves protein onto lean mass. activity, proteinGoal, targetBmi, and dailyDeficitKcal are optional.

Returns: both unit systems, BMI with WHO category AND the lower cutoffs WHO publishes for South and East Asian populations, every BMR estimate with the spread in calories and percent, a TDEE range, a protein range, an optional target and timeline, warnings, and a disclaimer field.

THIS IS NOT MEDICAL ADVICE and the response says so in its payload, not just on the page. Report the range and the disclaimer to the user. Do not present these figures as clinical guidance, and do not strip the caveats — they are the honest part of the answer.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
ageYesYears, 15-100. Outside that the equations do not apply.
sexYesRequired by the BMR equations, which are fitted separately.
heightYesHeight WITH a unit. Accepts 178cm, 1.78m, 5'10", 5 ft 10 in, 70in. A bare number is REFUSED because it is ambiguous.
weightYesWeight WITH a unit. Accepts 75kg, 165lb, 11st 8lb. A bare number is REFUSED.
activityNoActivity band, default sedentary. This is the LARGEST source of error in the estimate — most people overestimate. If between two bands, take the lower.
targetBmiNoTarget BMI, 15-40, to compute a goal weight.
proteinGoalNoWhich protein guidance range to report. Default maintenance.
bodyFatPercentNoOptional but worth supplying: adds the Katch-McArdle estimate, which uses lean mass, and moves the protein target onto lean mass.
dailyDeficitKcalNoDaily deficit, to estimate a timeline. The timeline is a lower bound.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Discloses far more than the readOnlyHint=true annotation: it reveals refusal behavior ('REFUSES unitless input instead of guessing'), input validation ('rejects biologically implausible values'), multi-formula returns with the spread as the measure of precision, and a disclaimer embedded in the payload. It also instructs the agent how to relay results ('Report the range and the disclaimer... do not strip the caveats'). No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Roughly 300 words, but deliberately structured: a one-line front-loaded purpose, two bolded rationale sections, then Input/Returns/safety sections. Given 9 parameters and no output schema — meaning return shape must be described in prose — the length is earned. Every section carries distinct information, and the closing safety directive is non-redundant.

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?

The tool is complex: 9 params, 3 enums, 4 required, and no output schema. The description covers required inputs, unit policy, optional-parameter effects, and the full return payload — both unit systems, WHO categories including Asian cutoffs, BMR spread, TDEE range, protein range, timeline, warnings, and disclaimer. Nothing an agent needs to invoke or relay this tool correctly is missing.

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. The description adds cross-parameter meaning beyond the schema: it flags bodyFatPercent as changing the estimation method (Katch-McArdle, protein moved onto lean mass), groups required versus optional inputs, and restates the unit-carrier requirement with concrete examples. That is genuine value-add, but each parameter is already well documented in the schema, so not a 5.

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?

Opens with a specific verb and resource: 'Compute BMI, energy expenditure, and protein targets from height and weight, with explicit error bounds.' The error-bounds qualifier pins down the tool's distinctive output style. No siblings exist, so nothing to differentiate against, but the purpose is unambiguous and complete.

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?

Explicitly directs the agent: 'Use this for any of those calculations rather than doing the arithmetic,' then justifies the directive with two concrete failure modes — unit ambiguity producing factor-of-two errors, and false precision from single-formula calculators. This is stronger than implied usage; it tells the agent when and why to delegate.

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

All Body Metrics toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.7/5.0
Disambiguation5/5

There is only one tool, so there is no possibility of confusing it with another endpoint. Its purpose is clearly described and distinct by default.

Naming Consistency4/5

The single name 'body_metrics' is clear and uses consistent snake_case, but it is a descriptive noun phrase rather than the verb_noun convention common in MCP servers. With only one tool there are no conflicting naming styles to penalize heavily.

Tool Count3/5

One tool is a borderline count; it feels thin for a server named Body Metrics even though the single tool is dense and well-designed. It works because all related calculations are bundled, but the surface lacks the modularity expected of a typical 3-15 tool MCP server.

Completeness5/5

For its declared scope, the tool covers BMI, BMR formulas, TDEE, protein targets, optional body-fat-adjusted estimates, and target timelines with proper caveats. No obvious dead-end or missing core operation exists in this stateless calculation domain.

Resources