Skip to main content
Glama

Fix an exercise's guide, video or sides

update_exercise
DestructiveIdempotent

Changes the how-to of an exercise you added: guide (setup, 2–6 steps, feel, avoid), the one-line instructions shown on the set screen, and videoUrl (an https link; null removes it). Give only what should change. It fixes a guide the athlete finds unclear or a video that is wrong or broken, and adds guides to exercises added before guides existed (list_exercises shows hasGuide: false). It also sets sides (together or each; see list_exercises) on one added without it; its start's bothSides must match. It can't change a library exercise, and it changes nothing else about the exercise. A different demo for one athlete, on any exercise including library ones, is set with set_exercise_video.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "id": "<id>"
    },
    "name": "update_exercise"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYes
guideNo
sidesNo
videoUrlNo
instructionsNo

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already flag destructive and idempotent behavior, and the description adds real context: partial updates ("Give only what should change"), null-removes semantics for videoUrl, a cross-field constraint that the start's bothSides must match, and a guarantee that nothing else about the exercise changes. It does not clarify whether supplying `guide` wholesale replaces the existing guide or merges into it, which matters for a destructive tool.

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

Conciseness4/5

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

Front-loads the mutation and field list, then follows with use cases and exclusions; nearly every clause carries information. It is dense with nested parentheticals and long sentences, which slows parsing slightly, but there is little genuine waste.

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 nested-object mutation with no output schema and only bare annotations, the description covers scope, triggers, constraints, and the alternative tool. The remaining gap is replace-vs-merge semantics for the nested guide object and what error behavior to expect when the exercise is a library one.

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?

With schema description coverage at 0%, the description carries the burden and largely succeeds: it explains the guide sub-fields (setup, 2–6 steps, feel, avoid), the purpose of `instructions`, the https format and null-removal for `videoUrl`, and the meaning of the two `sides` values. Only `id` is left implicit, which is self-evident from the required-parameter shape.

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 ("Changes the how-to of an exercise you added") and enumerates exactly which fields are mutable (guide, instructions, videoUrl, sides). It explicitly scopes out library exercises and names the sibling set_exercise_video for the per-athlete case, so the agent can tell it apart without opening schemas.

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 concrete trigger scenarios: fixing a guide the athlete finds unclear, a wrong or broken video, and backfilling guides on exercises where list_exercises shows hasGuide: false. It names the alternative (set_exercise_video) for the case this tool does not cover and states a precluded case (library exercises).

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources