LiftTrack

create_workout

Only call this after the user has reviewed the proposed workout (exercises, sets, loads, rest mode, supersets) and approved it. Present it for review the way your client supports and get explicit approval first: the LiftTrack app renders this tool's input as an interactive approval card the user accepts or rejects inline (no plaintext restatement needed there), while other clients should show a plaintext summary and confirm. See the server instructions for the full workflow.

Create a workout template. Use exact exercise names from search_exercises.

Each exercise: name, target (reps|time), load (weight|percent), working_rest_mode (timed|off|lap), working_rest_seconds (required when working_rest_mode is 'timed'; omit otherwise), optional warmup_sets[], optional warmup_rest_mode (required when warmup_sets is present; same allowed values as working_rest_mode), optional warmup_rest_seconds (required when warmup_rest_mode is 'timed'), working_sets[] (min 1), and an optional superset label. working_rest_mode 'off' means continue straight to the next set/exercise with no rest. 'lap' means the watch pauses until the user presses the lap button. The same rest setting applies between sets within the exercise and after the exercise's last set (the inter-exercise rest). Each set has reps (when target=reps) or seconds (when target=time), and weight (when load=weight) or percent (when load=percent), plus optional rpe. weight is in the user's units (0 = bodyweight). percent is the percentage of training max itself, e.g. 65 for 65% — pass the percentage, do NOT convert it to a weight. The server computes the weight from the user's training max, and the call fails with a clear error if the exercise has no training max set. superset is an optional short label (case-insensitive, max 16 chars). Exercises sharing a label run as one superset on the watch — at least two exercises must share a label, max 16 distinct labels per workout. Optional folder_name places the workout in that folder; if no folder has that name, one is created. Call get_folders first to reuse an existing folder.

Example with a two-exercise superset: {"name":"Push","exercises":[{"name":"Barbell Bench Press","target":"reps","load":"weight","working_rest_mode":"timed","working_rest_seconds":90,"working_sets":[{"reps":5,"weight":185}],"superset":"A"},{"name":"Cable Row","target":"reps","load":"weight","working_rest_mode":"lap","working_sets":[{"reps":8,"weight":80}],"superset":"A"}]}

Input Schema

TableJSON Schema

Name	Required	Description
`name`	Yes
`exercises`	Yes
`folder_name`	No	Optional folder to place the workout in. The folder is created if no folder has this name. Call get_folders to see existing folders.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`name`	Yes
`set_count`	Yes
`folder_name`	No
`exercise_count`	Yes
`folder_created`	Yes

Schema Changelog

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

First observedSep 9, 2026

TDQS

A5/5.0

Behavior5/5

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

The description goes well beyond the minimal annotations by explaining important behaviors: percent is passed as a percentage and the server computes weight, a missing training max produces a clear error, rest modes have precise meanings, and an unknown folder_name causes a new folder to be created. These are the kind of side effects and failure modes an agent needs to know before calling.

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?

The description is long, but every section earns its place: an approval gate up front, then parameter rules, then a concrete example. The structure is dense and scannable, and the example clarifies the conditional relationships better than prose alone would.

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 the tool's conditional complexity, the description is unusually complete. It covers prerequisites, required vs optional fields, server-side behavior, error conditions, and side effects, while the output schema handles the return shape. An agent has enough information to build a valid payload and to know when not to call the tool.

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

Parameters5/5

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

Even though schema description coverage is only 33%, the description compensates thoroughly. It explains conditional requirements (working_rest_seconds only with 'timed'), the meaning of weight=0 as bodyweight, the critical distinction between percent and computed weight, superset grouping constraints, and includes a full example JSON payload.

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?

The description clearly states the action ('Create a workout template') and the resource domain, and then adds enough specific detail about exercises, sets, and rest modes to make the tool's purpose unambiguous. It is easily distinguished from siblings like update_workout, delete_workout, and get_workout_templates.

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?

The description explicitly states when the tool may be called: only after the user has reviewed and approved the proposed workout. It also gives concrete workflow guidance, such as using exact exercise names from search_exercises and calling get_folders first to reuse an existing folder.

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

All LiftTrack tools Inspect

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.

Resources

Need Help?