Skip to main content
Glama
Sign In
Codemm

Codemm

by iignaite
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

save_track

Installs a learner-approved track, then validates it with offline probes, installing only if all gates pass.

Instructions

Install a track: track.yaml, a Dockerfile (a WASI track has none) and probe/ files. Building the image runs the Dockerfile WITH network access (a WASI track downloads its toolchain instead), so only install tracks the learner agrees to. Codemm then runs the probes with the network off and installs the track only if every gate passes; otherwise it returns what failed.

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": {
      "files": "<files>"
    },
    "name": "save_track"
  }
}

Input Schema

NameRequiredDescriptionDefault
filesYesFile map: { "relative/path": "file contents as text" }

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior5/5

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

With no annotations supplied, the description carries the full burden and does so well: it discloses that the image build runs the Dockerfile with network access, that WASI tracks download a toolchain instead, and that probes run with the network off. It also explains the atomic install semantics (installs only if every gate passes, otherwise returns what failed), which is exactly the side-effect and failure information an agent needs.

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?

One dense paragraph that front-loads the required file layout before moving to build and probe behavior; no filler sentences. It is slightly run-on across the Dockerfile/WASI clauses, which costs a point but not readability.

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 single-parameter tool with no output schema, the definition covers required inputs, network behavior, validation gates, and what comes back on failure. Nothing an agent needs in order to call it safely 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?

The schema already documents the single 'files' parameter at 100% coverage as a path-to-contents map. The description still adds value by naming the expected members of that map and flagging the WASI special case where no Dockerfile is included.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Install a track') and enumerates exactly what a track consists of: track.yaml, a Dockerfile (absent for WASI tracks), and probe/ files. That makes the scope unmistakable and separates it from the save_exercise/save_lesson/save_roadmap siblings, though it never names those alternatives explicitly.

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 a real gating condition: 'only install tracks the learner agrees to', which implies a consent prerequisite before calling. It does not spell out when a different save_* tool is the right choice, so routing must be inferred from the resource being a track.

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