Daily protein need by weight and goal, with a sample Indian food plan to hit it.
Scored across 2 tools
The two tools serve distinct purposes: one calculates protein requirements, the other generates a food plan. Descriptions explicitly state when to use each, and their example queries do not overlap.
Both tool names use a consistent snake_case pattern with the 'protein_' prefix, making the set predictable and easy to parse.
Two tools is on the thin side for the domain; while each earns its place, the server could benefit from additional supporting tools for a more complete experience.
The core operations—requirement calculation and sample meal planning—are covered well. Minor gaps exist, such as customizing plans for specific dietary restrictions or looking up individual food protein values.
Use this when someone asks how to get a protein amount from Indian food, such as "how to get 80 g protein a day vegetarian", "high protein Indian veg foods for 100 g" or "eggetarian 90 g protein sample day". Builds a sample day from dal, paneer, curd, soya, milk, eggs, chicken and fish. Do not use for medical diets, kidney disease, allergies, or supplement questions.
| Name | Required | Description | Default |
|---|---|---|---|
| diet | Yes | Diet type: veg, eggetarian or non_veg | |
| grams | Yes | Daily protein target in grams |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds real value beyond that: the content domain (the specific foods used per diet type) and hard scope boundaries (no medical diets, kidney disease, allergies, supplements), which tells the agent when to refuse.
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?
Front-loaded with the usage trigger, followed by the output scope and exclusions. The three example queries are slightly redundant with each other but serve keyword-matching value; no filler sentences.
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 no output schema, the description carries the burden of explaining what comes back, and it does so at a high level ('builds a sample day' from named foods). It is adequate for a two-parameter, read-only generator, though it could say more about the shape of the returned plan.
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 grams (20-250) and the diet enum fully documented in the schema. The description's food list loosely maps to the diet enum (veg/eggetarian/non_veg) but adds no format, unit, or constraint detail beyond the schema, so 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?
States a specific verb and resource: it 'builds a sample day' of Indian protein food from a named food list (dal, paneer, curd, soya, milk, eggs, chicken, fish). An agent knows exactly what it produces, but the description never names or contrasts with the sibling protein_per_day, so the two are not explicitly disambiguated.
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 explicit triggering contexts with three quoted user phrasings ('how to get 80 g protein a day vegetarian', etc.) plus explicit exclusions (medical diets, kidney disease, allergies, supplements). The one gap is that it does not point to protein_per_day as the alternative for non-sample or per-food calculations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Use this when an adult asks how much protein they need a day, such as "how much protein per day for 70 kg", "protein for weight loss 80 kg woman" or "protein intake to build muscle 65 kg". Do not use for children, pregnancy, kidney or liver disease, medical diets, or supplement and medication questions.
| Name | Required | Description | Default |
|---|---|---|---|
| goal | Yes | Goal: maintain, weight_loss or muscle_gain | |
| height_cm | No | Optional height in centimetres; above BMI 25 the target uses the weight at BMI 25 | |
| weight_kg | Yes | Body weight in kilograms |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds only clinical scope limits, which are already credited under usage guidelines; it discloses nothing about the calculation's basis or the shape of the answer.
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 sentences, front-loaded with the use condition followed by the exclusion list. The example queries are compact and disambiguating rather than filler, so every sentence earns its place.
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?
Scope and applicability are well covered, but with no output schema the description should say what is returned (e.g. grams of protein per day) and how the value derives from weight/goal. That return-format gap leaves the definition only adequate for a calculator that produces a numeric recommendation.
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 goal, weight_kg and height_cm (including the BMI 25 adjustment) are fully documented in the schema. The description's example phrases loosely hint at weight/goal combinations but add no syntax or unit meaning beyond the schema, so the baseline 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?
Names the specific resource (daily protein requirement) and the population (adults) with three concrete example queries, so an agent can match natural-language asks directly. It is easily distinguishable from the sibling protein_food_plan, which implies meal construction rather than a per-kilogram target.
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?
Explicitly states when to use ('an adult asks how much protein they need a day') and enumerates when NOT to use: children, pregnancy, kidney or liver disease, medical diets, and supplement/medication questions. This is a genuine when/when-not boundary, not an implied one.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
protein_food_planprotein_per_dayWaist size health check (Indian cutoffs) and the waist size to stay under.
BMI check with Indian (Asian) cutoffs and a healthy weight range for any height.
GLP-1 calorie and protein targets with a dose aware appetite ceiling, plus food and recipe search.
Daily calorie target to lose, keep or gain weight, plus a weight goal timeline.
Add one secure layer between your agents and this server.