Dr. Dotzauer Calculators

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

No annotations are provided, so the description carries the full behavioral burden. It reveals that the calculation supports three paces and a deadline check, but it does not state that this is a pure read-only calculator, what the return values look like (e.g., duration per tempo), or any assumptions such as goal weight needing to be below current weight.

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

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

The description is compact and front-loaded: the core calculation is stated first, followed by the optional deadline check and a reference URL. It is efficient, though the external website reference adds little value for an agent and could be omitted without loss.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given three parameters, no annotations, and no output schema, the description is minimally adequate. It implies that the tool returns duration for three paces, but it does not explicitly describe the output structure or the deadline-check behavior in enough detail for an agent to fully understand the return values.

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

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

Schema description coverage is 100%, so the parameter meanings are already fully documented in the input schema. The description adds context about the three weight-loss tempos and the optional deadline check, but it does not add syntax, units, or constraints beyond what the schema provides. Baseline 3 applies.

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

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

The description clearly states that the tool computes the duration until goal weight at three tempos (0.5 / 1 / 1.5 % body weight per week), optionally with a deadline check. It distinguishes itself from sibling calculators by focusing specifically on weight-loss duration rather than BMI, calorie deficit, or ideal weight, though it does not explicitly name those siblings.

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

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

The description implies usage by mentioning an optional deadline check, but it gives no explicit guidance on when to choose this tool over siblings like kaloriendefizit or idealgewicht. There are no stated prerequisites, exclusions, or alternative-tool routing.

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

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

No annotations are provided, so the description carries the full behavioral burden. It discloses that the calculation uses WHO adult classification, which is useful context, but it does not explicitly describe the return values (e.g., BMI plus category) or any other behavioral traits.

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

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

The description is two short sentences, front-loaded with the core purpose and followed by a useful reference. There is no filler or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple two-parameter calculator with complete schema coverage, the description gives enough context to invoke it correctly, including the WHO adult classification scope. The main minor gap is that it does not explicitly state what the tool returns, though the classification mention strongly implies it.

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

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

Schema description coverage is 100%, with both weight_kg and height_cm documented as 'Gewicht in kg' and 'Größe in cm'. The description adds no parameter-level detail beyond the schema, so the baseline of 3 is appropriate.

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

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

The description clearly states that the tool computes Body-Mass-Index (kg/m²) with WHO classification for adults, and references the corresponding online calculator. The verb is implicit in the calculator context, but the resource and scope are clear enough to distinguish it from siblings like ffmi or koerperfett_navy.

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

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

The description does not say when to use this tool versus the many sibling health calculators, nor does it give any exclusions or prerequisites. Usage is only inferable from the name and the mention of WHO classification.

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

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

With no annotations, the description carries the full burden, and it does disclose the calculation method (mean of Epley and Brzycki) and points to a reference implementation. However, it does not state output units/format (kg?), what happens outside the 2–12 rep range, or error behavior for reps=1.

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

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

A single front-loaded sentence with the method in parentheses and no wasted preamble. The external website reference is mildly promotional but does provide a verification anchor.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter pure calculator with no output schema, the description covers inputs, method, and the two returned quantities. Missing only boundary behavior and explicit output units, which are minor for this complexity.

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

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

Schema coverage is 100% and already documents both parameters including the 2–12 rep range, so the description adds little beyond restating 'Gewicht × sauberen Wiederholungen'. Baseline 3 applies when the schema does the heavy lifting.

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

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

States a specific verb (estimate) and resource (1RM and 5RM equivalent) plus the exact inputs (weight × clean reps) and the method (mean of Epley and Brzycki). This is clearly distinguishable from siblings like kraftwerte (strength standards) or kalorienverbrauch.

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

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

Usage is only implied by the input description ('aus Gewicht × sauberen Wiederholungen'); there is no explicit statement of when to pick this over kraftwerte or other siblings, and no exclusions or prerequisites. An agent can infer the context but is not routed.

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

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

With no annotations, the description carries the full disclosure burden. It helpfully pins down the formula lineage (Kouri 1995, factor 6.3) and the 1.80 m normalization, and referencing a public calculator supports verification, but it never states what exactly comes back (single normalized FFMI? lean mass in kg? both?) or how out-of-range body fat behaves.

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

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

A single densely packed sentence, front-loaded with the metric name and followed by inputs, normalization, citation, and a reference implementation. No filler, though the run-on construction makes the return-value intent hard to parse at a glance.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a three-parameter pure calculator with no annotations and no output schema, the description is adequate on inputs and method but leaves the output shape ambiguous: it names 'FFMI und Magermasse' without saying whether both are returned, in what units, or whether a non-normalized FFMI is also included.

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

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

All three parameters are fully described in the schema (100% coverage), so the schema already does the work and a 3 is the baseline. The description adds the conceptual mapping that these three values produce FFMI plus lean mass, but supplies no syntax, rounding, or range details beyond the schema.

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

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

States a specific computed metric (FFMI and lean mass) and the exact inputs it derives from (weight, height, body fat), plus the normalization convention and source paper. It is clearly distinguishable from siblings like bmi or koerperfett_navy, though it never explicitly contrasts itself with them.

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

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

There is no statement of when to use this versus bmi, koerperfett_navy, or idealgewicht, and no mention of preconditions or valid input ranges beyond what the schema enforces. The only contextual anchor is a pointer to an external calculator for parity, which does not guide tool selection.

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

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

With no annotations, the description does carry some behavioral weight: it discloses the calculation method (two formulas compared) and that results vary by activity level, which is real information for a compute tool. However, it says nothing about output units (kcal), what the Harris-Benedict comparison actually returns, or whether the two formulas are returned side by side.

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

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

Two short sentences with the purpose and method front-loaded and no filler. A single ambiguous phrase ('je Aktivitätslevel') is the only element that costs clarity rather than characters.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema, no annotations, and 40% parameter coverage leave important gaps: the description never states what is returned (a single BMR value, a formula comparison, TDEE for the chosen level or a table across levels) or in what units. For a five-parameter calculation tool this is under-specified.

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

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

Schema coverage is only 40%, so the description needs to compensate and largely does not. The phrase 'je Aktivitätslevel' hints that activity drives TDEE, but sex, height_cm, and weight_kg are undocumented in both schema and description, and no ranges, units, or defaults are restated beyond what the enum fields already show.

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

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

The description names a specific computed resource (Grundumsatz/BMR and Gesamtumsatz/TDEE) and even the formulas behind it (Mifflin-St-Jeor plus Harris-Benedict comparison), which an agent can distinguish from siblings like bmi or ffmi. It does not explicitly differentiate from the closest neighbor, kalorienverbrauch, so it stops short of a 5.

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

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

There is no statement of when to use this versus kalorienverbrauch, kaloriendefizit, or kalorienbedarf-style siblings, and no prerequisites or exclusions. The only usage cue is a reference to an external web calculator, which is implied context rather than guidance.

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

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

No annotations are provided, so the description carries the burden. It does disclose the underlying method (WHO-style BMI band 18.5–24.9) and anchors to a public reference calculator, which signals a deterministic read-only computation. It does not state that the output is a lower/upper bound pair or that no persistence occurs.

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

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

Two compact sentences, front-loaded with the result unit and the formula band. The website reference earns its place as a spec anchor rather than filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter deterministic calculator with full schema coverage and no output schema, the description supplies the missing formula detail (the 18.5–24.9 band and kg units), so an agent can predict the return. Only the exact shape of the returned range is left implicit.

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

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

Schema coverage is 100% and the single parameter already documents 'Größe in cm', so the description adds only the restatement 'für eine Körpergröße'. Baseline 3 applies when the schema does the heavy lifting.

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

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

States a specific computation: a healthy weight range in kg derived from a height via the BMI band 18.5–24.9. That distinguishes it from pure single-value siblings like bmi or ffmi, though it never names an alternative explicitly.

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

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

Usage is implied by the input (a height), but there is no explicit statement of when to pick this over bmi or koerperfett_navy, nor any prerequisites or exclusions. An agent must infer the choice from the sibling names.

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

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

With no annotations, the description carries the full burden and does meaningful work: it discloses the returned artifacts (TDEE, three deficit tiers, weekly loss, protein target) and a safety gate that suppresses numeric targets for minors or underweight users. It stops short of naming the underlying BMR formula or how activity factors are applied, which would matter for a health calculation.

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

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

Three tight sentences, front-loaded with the computed output and followed by the constraint and the reference link. The website reference sentence is the least informative element but is short enough not to hurt.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 5-parameter calculation tool with no output schema and no annotations, the description conveys what comes back and the key guardrail. The remaining hole is methodological detail (which BMR equation, how activity multipliers map) and undocumented body-measurement parameters.

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

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

Schema coverage is only 40%: activity (default light) and age range are documented in the schema, but sex, height_cm and weight_kg have no descriptions anywhere. The description adds no unit, format or interpretation guidance, only an oblique reference to age/BMI via the adult gate, so it does not compensate for the gap.

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

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

The description names a specific computation: TDEE plus three named deficit tiers (−15/−20/−25 %), expected weekly weight loss and a protein target. That clearly separates it from siblings like grundumsatz (BMR only) or kalorienverbrauch, although no sibling is named explicitly.

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

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

The use case (planning a calorie deficit) is implied by the content described, and the mention of a reference calculator gives context. However, there is no explicit statement of when to choose this over grundumsatz or kalorienverbrauch, and no prerequisites or exclusions beyond the adult gate.

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

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

No annotations exist, so the description carries the full burden; it discloses the actual computation (kcal = MET × kg × Stunden) and anchors behavior to a public reference calculator. It omits edge-case behavior for out-of-range duration or unknown activity and says nothing about result rounding, which keeps it below 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.

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

Three short sentences, scope and formula front-loaded, exclusions in the middle. The website reference is the only soft sentence, serving as a behavioral calibration anchor rather than filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a four-parameter pure calculation with no output schema, the description supplies the formula so the agent can predict the return value, and the schema covers the enum list and met-override. Missing only error/validation behavior for out-of-range inputs (1–600 min is in the schema).

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

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

Schema coverage is 75% and the schema already documents met, activity and duration_min, so the baseline is 3. The formula in the description clarifies what weight_kg and duration_min are actually consumed by, adding modest value beyond the field descriptions.

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

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

States a specific computed quantity ('Kalorienverbrauch EINER Sport-/Alltagsaktivität') and its method (MET-basiert), and explicitly distinguishes it from the two sibling tools an agent might confuse it with (grundumsatz, kaloriendefizit). The uppercase 'EINER' reinforces the single-activity scope.

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

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

Gives an explicit negative condition ('Nicht der Gesamtumsatz') plus a named alternative route for that case ('dafür grundumsatz/kaloriendefizit nutzen'), which are both present in the sibling list. The agent can route between tools without opening a schema.

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

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

No annotations, so the description carries the load; it does disclose that the result includes a neutral category classification and that the formula matches a known public calculator, implying deterministic, side-effect-free computation. It never explicitly states that nothing is stored or that the tool is a pure calculation, and it gives no detail on the returned category boundaries.

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

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

One front-loaded sentence with the method and inputs, plus a short provenance clause; dense but every clause carries information. The formula-source sentence is the weakest earner but adds reproducibility value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 5-parameter calculation tool with full schema coverage and no output schema, the description supplies what is missing: what is computed, which method, and that a category classification is returned. Only the format of the category output remains unspecified, a minor gap.

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

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

Schema description coverage is 100%, so the schema already documents each measurement including the conditional hip requirement for females. The description's enumeration of the same measurements adds no semantics beyond the schema, making the baseline 3 appropriate.

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

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

States a precise verb and resource ('Körperfettanteil (%) ... berechnen') and names the exact method (US-Navy-Umfangmethode) plus the required measurements. It is clearly distinguishable from siblings like bmi or ffmi, though it never explicitly contrasts itself with them.

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

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

The listed inputs imply when the tool applies (you need circumference measurements), but there is no explicit when-to-use/when-not guidance and no pointer to the alternative calculators (bmi, ffmi, idealgewicht) that share this domain.

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

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

No annotations exist, so the description carries the full burden. It does disclose the unit conventions (5RM in kg, pull-ups in reps) and anchors behavior to a known public calculator, which helps predict results, but it never says what happens when optional lifts are omitted or how the 'Gesamtbewertung' is derived from partial input.

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

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

Two compact sentences that front-load the output scope and end with the helpful reference implementation. There is mild redundancy with the property descriptions, but no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With eight parameters, no annotations and no output schema, the description should say more about the return value than 'plus Gesamtbewertung' — e.g. whether each lift gets its own Anfänger/Fortgeschritten/Elite classification and how missing lifts affect the total. The core intent is clear, but an agent cannot fully anticipate the response shape.

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

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

Schema coverage is 88%, so almost every parameter is already documented with unit and rep scheme. The only added meaning is that results are computed relative to bodyweight, clarifying bodyweight_kg's role as the denominator; the rest of the sentence simply re-lists parameters the schema already describes.

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

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

The description names the concrete resource (strength standards relative to bodyweight for squat, bench, deadlift, row, overhead press and pull-ups) plus an overall rating, and even cites the reference calculator. That is far more specific than a sibling like 'bmi' or 'einrm', though it never explicitly contrasts itself with einrm (1RM) or the other body-metric siblings.

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

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

Nothing states when to call this instead of einrm or the other fitness siblings, nor any preconditions such as which lifts must be supplied. The reader can infer that you pass whatever 5RM values you have and get a rating, but that inference is left entirely to the schema.

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

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

With no annotations, the description carries the full burden, and it does disclose the output form (a range in g/day) and the underlying basis (Morton 2018 factors). It does not mention validation behavior, rounding, or how wide the range is, so it is strong but not complete.

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

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

Two short sentences, front-loaded with the output and its unit, followed by the input basis and source. The website reference is compact and useful rather than filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple three-parameter calculator with no output schema, the description conveys output type, unit and methodology, which is enough to invoke it confidently. Only minor gaps remain around output shape and edge-case handling.

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

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

Schema coverage is 67%: goal has a weak description ('Ziel') but an enum, active explains its default and that it only matters for goal=erhalt, and weight_kg is self-documenting via its unit suffix. The description reinforces the three inputs and their roles, adding marginal value over the schema.

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

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

States precisely what is computed: daily protein requirement as a range (g/day) from weight, goal and activity. This is clearly distinguishable from sibling calculators like bmi, ffmi or grundumsatz. It stops short of naming a sibling explicitly, but the resource is specific enough for an agent to pick it correctly.

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

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

Usage is only implied by the topic ('daily protein requirement'); there is no statement of when to prefer this over grundumsatz or kaloriendefizit, nor any exclusions. The reference to the website calculator gives context but not routing guidance.

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