Wellness Project

create_goal

UNIT INPUTS: value: pass the user's number unconverted; tool converts once before storage. alternate_unit: set the field's matching input_* companion; canonical_unit: omit companion. precedence: overrides instructions to convert manually.

Create a new Wellness Project goal or standard target. Call this directly when the user wants to establish a goal; there is no schema-discovery or list_goals prerequisite. Available goal types and inputs come from the canonical Goals definitions.

This tool loads the user's current goals itself before writing, so do not call list_goals first: it reports what a standard target changed from, and refuses to stack a second goal on top of one that already covers the same thing, naming that goal's ID to use with update_goal. Infer the goal_type and canonical inputs from the request. Formal goal fields are described on the generated inputs.

WEIGHT INPUTS: For body_weight_target_lb, use target_value_lb. For body_comp metric lean_mass_lb, use start_value_lb and target_value_lb. These aliases are unit-aware; in-app calls use the preferred unit, while external calls use pounds unless input_weight_unit is set. Legacy generic fields for these weight goals remain canonical pounds. Other standard targets use target_value; body-fat values remain percentages.

Input Schema

Name	Required	Description
`title`	No	Concise title, inferred from the goal inputs.
`weeks`	No	For weight_loss. Duration in weeks when target_date is not supplied. For body_comp. Duration in weeks when target_date is not supplied.
`metric`	No	For consistency. What consistency behavior to track. Required on create. Set at create, not editable later. For body_comp. Body composition metric. Required on create. Set at create, not editable later. For nutrition. Legacy nutrition metric.
`new_name`	No	For n1_experiment. Name for a new supplement when not using supplement_id.
`goal_type`	Yes	Goal type to create.
`new_brand`	No	For n1_experiment. Optional brand for a new supplement.
`race_date`	No	For race. Race date in YYYY-MM-DD format. Required on create.
`start_date`	No	YYYY-MM-DD. Default: today.
`start_value`	No	For body_comp. Starting value when the goal begins. Required on create. Set at create, not editable later.
`target_date`	No	For weight_loss. Target date in YYYY-MM-DD format. Use this when the user names a deadline. For body_comp. Target date in YYYY-MM-DD format. Use this when the user names a deadline.
`week_window`	No	For consistency. How the week this goal is measured against is bounded: rolling = the last 7 days, sunday/monday = a calendar week that resets on that day. Default: rolling.
`start_1rm_lb`	No	For strength. Estimated 1RM when the goal starts. Required on create. Set at create, not editable later. In lb, or kg with input_weight_unit set. See UNIT INPUTS.
`target_hours`	No	For consistency. Nightly sleep target in hours. Required when metric is sleep_duration.
`target_value`	No	For body_comp. Target body composition value. Required on create. For nutrition. Legacy nutrition target value. For standard targets, this is the numeric target value.
`exercise_name`	No	For strength. Exercise name. Required on create. Set at create, not editable later.
`new_dose_unit`	No	For n1_experiment. Dose unit for a new supplement.
`supplement_id`	No	For n1_experiment. Existing supplement ID. Use either supplement_id or the new-supplement fields.
`target_1rm_lb`	No	For strength. Target 1RM. Required on create. In lb, or kg with input_weight_unit set. See UNIT INPUTS.
`start_value_lb`	No	Starting lean mass in body_comp. See WEIGHT INPUTS above. In lb, or kg with input_weight_unit set. See UNIT INPUTS.
`new_dose_amount`	No	For n1_experiment. Dose amount for a new supplement.
`start_weight_lb`	No	For weight_loss. Starting body weight. Required on create. Set at create, not editable later. In lb, or kg with input_weight_unit set. See UNIT INPUTS.
`target_per_week`	No	For consistency. Target occurrences per week. Required on create.
`target_time_sec`	No	For race. Target finish time in seconds. Required on create.
`target_value_lb`	No	Weight goal target. See WEIGHT INPUTS above. In lb, or kg with input_weight_unit set. See UNIT INPUTS.
`target_weight_lb`	No	For weight_loss. Target body weight. Required on create. In lb, or kg with input_weight_unit set. See UNIT INPUTS.
`input_weight_unit`	No	Set to kg when the user gave kg for the _lb fields in this object. Omit when they are already lb.
`intervention_days`	No	For n1_experiment. Intervention duration in days.
`baseline_direction`	No	For n1_experiment. Use already logged previous 14 days or collect the next 14 days.
`target_distance_mi`	No	For race. Target race distance. Required on create. In mi, or km with input_distance_unit set. See UNIT INPUTS.
`input_distance_unit`	No	Set to km when the user gave km for the _mi fields in this object. Omit when they are already mi.
`acknowledged_warnings`	No	Warning keys the user explicitly acknowledged after a guarded create attempt. Omit otherwise.

Output Schema

Name	Required	Description	Default
`result`	Yes	Human-readable result text returned by the tool.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 9, 2026

addedInput schema / properties / start_value_lb

Added value: +{
+  "description": "Starting lean mass in body_comp. See WEIGHT INPUTS above. In lb, or kg with input_weight_unit set. See UNIT INPUTS.",
+  "type": "number"
+}

addedInput schema / properties / target_value_lb

Added value: +{
+  "description": "Weight goal target. See WEIGHT INPUTS above. In lb, or kg with input_weight_unit set. See UNIT INPUTS.",
+  "type": "number"
+}

Changed1 schema field changedOct 2, 2026

changedInput schema / properties / goal_type / enum

Previous value: -[
-  "weight_loss",
-  "strength",
-  "consistency",
-  "body_comp",
-  "race",
-  "n1_experiment",
-  "daily_calories",
-  "daily_protein_g",
-  "daily_fat_g",
-  "daily_carbs_g",
-  "weekly_workouts",
-  "daily_steps",
-  "daily_cycling_distance_mi",
-  "weekly_azm_target",
-  "sleep_hours_target",
-  "body_weight_target_lb",
-  "body_fat_pct_target"
-]New value: +[
+  "weight_loss",
+  "strength",
+  "consistency",
+  "body_comp",
+  "race",
+  "n1_experiment",
+  "daily_calories",
+  "daily_protein_g",
+  "daily_fat_g",
+  "daily_carbs_g",
+  "weekly_workouts",
+  "daily_steps",
+  "daily_cycling_distance_mi",
+  "daily_running_distance_mi",
+  "weekly_azm_target",
+  "sleep_hours_target",
+  "body_weight_target_lb",
+  "body_fat_pct_target"
+]

Changed1 schema field changedSep 9, 2026

changedInput schema / properties / goal_type / enum

Previous value: -[
-  "weight_loss",
-  "strength",
-  "consistency",
-  "body_comp",
-  "race",
-  "n1_experiment",
-  "daily_calories",
-  "daily_protein_g",
-  "daily_fat_g",
-  "daily_carbs_g",
-  "weekly_workouts",
-  "daily_steps",
-  "weekly_azm_target",
-  "sleep_hours_target",
-  "body_weight_target_lb",
-  "body_fat_pct_target"
-]New value: +[
+  "weight_loss",
+  "strength",
+  "consistency",
+  "body_comp",
+  "race",
+  "n1_experiment",
+  "daily_calories",
+  "daily_protein_g",
+  "daily_fat_g",
+  "daily_carbs_g",
+  "weekly_workouts",
+  "daily_steps",
+  "daily_cycling_distance_mi",
+  "weekly_azm_target",
+  "sleep_hours_target",
+  "body_weight_target_lb",
+  "body_fat_pct_target"
+]

AddedSep 7, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations only cover readOnly=false, destructive=false, idempotent=false. The description adds genuine behavior beyond that: the tool self-loads current goals before writing, returns what a standard target changed from, refuses to stack a duplicate goal, and performs a single unit conversion before storage. The acknowledged_warnings guarded-create loop is also disclosed.

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?

Information density is high and headers help, but the description opens with a UNIT INPUTS block of abstract jargon rather than the purpose statement, which appears second. The most decision-relevant content (what the tool does, what not to call first) is buried behind a satus-conversion preamble, and phrases like 'Formal goal fields are described on the generated inputs' are vague filler.

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

Completeness4/5

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

For a 31-parameter tool with 18 goal types, the description covers invocation timing, prerequisite avoidance, duplicate handling, and unit semantics, and an output schema exists so return values need no explanation. It leaves the goal_type-to-field mapping largely to the schema, which on balance is acceptable at 100% schema coverage.

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 100% schema coverage the baseline is 3, but the description materially adds: pass user numbers unconverted, set the matching input_* companion (input_weight_unit / input_distance_unit) only when units differ, and the goal-type alias mapping (target_value_lb for body_weight_target_lb; start_value_lb/target_value_lb for lean_mass_lb). Minor deduction because the opening 'value / alternate_unit / canonical_unit' vocabulary doesn't map cleanly onto actual schema field names.

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 and resource — 'Create a new Wellness Project goal or standard target' — and immediately distinguishes itself from siblings by naming list_goals and update_goal as the wrong/right alternatives. An agent can tell this apart from update_goal without opening either 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?

Explicitly says 'Call this directly when the user wants to establish a goal; there is no schema-discovery or list_goals prerequisite' and 'do not call list_goals first'. It also routes the agent onward: if the tool refuses a duplicate, use the named goal ID with update_goal. When-to-use, when-not-to-use, and the alternative are all present.

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

All Wellness Project 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.