AIm

Add or update an exercise

upsert_exercise

Idempotent

Create or update an exercise in your catalog. Reuse a pool slug to keep one identity and history; when no pool match exists, provide complete details so the exercise is usable.

Instructions

Create or update an exercise in the user's catalog (keyed by its id/name). Prefer a pool exercise: call search_exercise_pool first and pass its slug as the id plus pool_slug, so the movement keeps one identity and one history. Only hand-write an exercise when the pool genuinely has nothing for it — then always set instructions (2-3 short technique cues, in the user's language), primary_muscles, category and equipment: the muscle map and the app UI are blank without them. Fields you omit are left as they are, so a partial update is safe.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`exercise`	Yes

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.2.1Sep 14, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations already signal idempotentHint=true and destructiveHint=false, and the description adds genuinely new behavioral context: omitted fields are preserved, pool exercises keep one identity/history, and hand-written exercises leave the UI blank unless certain fields are provided. 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?

Three focused sentences, each earning its place: the core upsert behavior, the pool-first workflow, and the required fields plus partial-update safety. Critical guidance is front-loaded before less common constraints.

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?

For a complex nested-object tool, the description covers creation, update semantics, pool integration, required metadata, and partial-update behavior. An output schema is present, so the description does not need to explain return values, and the workflow guidance is sufficient for an agent to call this tool correctly alongside its siblings.

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 description coverage is 0%, so the description must compensate, and it does for the most important fields: it explains the role of id and pool_slug, and mandates instructions, primary_muscles, category, and equipment for hand-written exercises. It does not explain every nested property, but the remaining property names are largely self-descriptive against the enum schemas.

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 clear action ('Create or update an exercise') on a specific resource ('the user's catalog'), and explains the keying mechanism ('by its id/name'). It also differentiates itself from search_exercise_pool by naming that sibling explicitly and positioning this tool as the write-side counterpart.

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?

Gives explicit routing guidance: prefer the pool by calling search_exercise_pool first, pass the pool slug as id plus pool_slug, and only hand-write when the pool has nothing. It also states when full metadata is required and that partial updates are safe.

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