Skip to main content
Glama
Sign In
Tennis Evolution

Tennis Evolution

by bobobo2026
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Render a labeled tennis highlight reel

start_highlight_reel

Start a background pipeline that turns a tennis recording into keyframe-aligned rally clips, plain and labeled highlight reels, and a manifest; returns a job ID to poll.

Instructions

Start the full pipeline in the background: lossless keyframe-aligned clips, a plain reel, a labeled reel (hit count / venue / wall clock / source timestamp) and manifest.json with self-check results. Returns a job_id; poll get_job. A 47-minute iPhone HDR recording with 5 rallies takes 3-5 minutes on an M-series Mac.

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": {
      "video": "<video>",
      "outdir": "<outdir>"
    },
    "name": "start_highlight_reel"
  }
}

Input Schema

NameRequiredDescriptionDefault
topNoKeep the N best rallies (0 = all; free version caps at 5).
sortNoRanking: longest rally first (hits), longest clip, or chronological.hits
unitNoHit counter unit (default 拍; 'hits').
codecNohevc
placeNoVenue text for the label.
videoYesLocal source recording.
labelsNo
outdirYesOutput directory (created).
timezoneNoIANA timezone for the wall clock, e.g. Asia/Shanghai.
source_labelNoPrefix for the source timestamp (default 片源; 'Source').
highlights_pathNoPath to a rally list (.txt from sliceapp or .json).
highlights_textNoRally list pasted inline, one rally per line, e.g. '27:14 - 28:08 40 hits'. Use either this or highlights_path.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations, the description carries the burden well: it discloses async background execution, the job_id/polling model, the exact output set including a self-check manifest, and a concrete runtime expectation (3-5 minutes for a 47-minute HDR recording). It omits failure modes, overwrite behavior in outdir, and resource/disk implications.

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 tight sentences, front-loaded with the pipeline outcome, then the polling contract, then the cost estimate. Nothing is padding.

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 12-parameter job-starting tool with no output schema and no annotations, the description covers the artifact set, async model, and runtime expectation. It leaves the input-source choice (precomputed rally list vs. auto-detection) and output directory side effects unaddressed, which an agent would otherwise need.

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

Parameters3/5

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

Schema coverage is 83%, so parameters are largely self-documenting. The description adds the useful detail that the labeled reel embeds hit count, venue, wall clock, and source timestamp (which maps to place/timezone/labels), but gives no direct guidance on highlights_path vs highlights_text or the top/sort interaction. Baseline 3 is appropriate.

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 (start) and resource (full highlight reel pipeline), and enumerates the concrete artifacts produced: keyframe-aligned clips, plain reel, labeled reel, and manifest.json. An agent can distinguish this from probe_video or rank_highlights purely from the description.

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?

Clearly frames this as the entry point for the full pipeline and tells the agent the follow-up path ('Returns a job_id; poll get_job'). It does not explicitly say when to prefer rank_highlights or probe_video first, but the 'full pipeline' framing implies the relationship.

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

Deploy Server

Other Tools