Skip to main content
Glama

Choose the athlete's demo video for an exercise

set_exercise_video
DestructiveIdempotent

Chooses the demo video the app plays for one exercise, for this athlete only. Works on any exercise in list_exercises, library ones included: it changes the athlete's choice, not the exercise. url is a YouTube video link (youtube.com/watch?v=…, youtube.com/shorts/…, youtu.be/…), stored in its plain form; other sites are refused, since the app plays the video in its own player. null clears the choice, and the app goes back to the exercise's own video or offers a search. reason is kept in the audit log. The phone gets it on its next sync. The newest choice wins, so a video the athlete picks later replaces this one, and this one replaces theirs.

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": {
      "exerciseId": "<exerciseId>",
      "url": "<url>",
      "reason": "<reason>"
    },
    "name": "set_exercise_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesa YouTube video link: youtube.com/watch?v=…, youtube.com/shorts/…, or youtu.be/…; null clears the athlete's choice
reasonYes
exerciseIdYes

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only give the safety profile (write, destructive, idempotent); the description adds real behavior: only YouTube URLs accepted and other sites refused, URL stored in plain form, null reverting to the exercise default or a search, reason written to an audit log, and the phone picking it up on next sync. Last-write-wins precedence is also disclosed, which is exactly the kind of conflict behavior annotations cannot convey.

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 core action and actor scope, then layers validation, null semantics, and sync behavior efficiently. The closing sentence restates 'newest choice wins' twice, which is the one redundant stretch.

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 three-parameter mutation with no output schema, it covers validation, clearing, audit, and propagation. It omits what a caller sees on rejection (error shape) and whether a return value exists, but nothing essential to correct invocation is missing.

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 only 33% schema coverage, the description carries most of the load and does: accepted URL formats, null-clears semantics, enforcement of YouTube-only, and that reason lands in the audit log. exerciseId gets only indirect treatment ('one exercise', 'any exercise in list_exercises') without saying what happens on an unknown id.

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 (chooses) and resource (demo video for one exercise) narrowed to 'this athlete only', and explicitly contrasts with changing the exercise itself. An agent can distinguish it from update_exercise or add_exercise without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear context: works on any exercise from list_exercises, library exercises included, and null clears the choice. The contrast clause 'it changes the athlete's choice, not the exercise' implicitly routes exercise-level edits elsewhere, but no sibling is named for that case, so it stops short of explicit alternatives.

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