Skip to main content
Glama
Sign In
SensorForge MCP Server

SensorForge MCP Server

by sidupreti
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Download a run's result

download
Idempotent

Unpack a completed run's results into your project, including the TensorFlow Lite Micro model, C sources, and report, while blocking writes to non-empty folders unless overwrite is enabled.

Instructions

Download a finished run's result and unpack it into the project: the model for TensorFlow Lite Micro, its C sources (c/: the model as a C array, the operator list, integration notes) and the report. Refuses to write into a folder that is not empty unless overwrite=True. Returns each file and what it is for.

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": {
      "run_id": "<run_id>"
    },
    "name": "download"
  }
}

Input Schema

NameRequiredDescriptionDefault
folderNoWhere to unpack. Default: <the model's folder>/sensorforge/<run id>/ (the working directory's when the model is unknown).
run_idYesThe run id of a lossless or optimize run that passed.
overwriteNoReplace files already in the folder.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

Beyond the annotations, the description discloses the key behavioral fact an agent needs: it refuses to write into a non-empty folder unless overwrite=True, which is a caller-visible failure mode the annotations do not convey. It also states the return shape (each file plus its purpose) for a tool with no output schema. The one tension is that overwrite=True replaces existing files while destructiveHint=false, though this is opt-in and guarded, so it is a nuance rather than a contradiction.

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?

Two sentences, front-loaded with the action and the deliverable inventory, then the overwrite constraint. The parenthetical listing the c/ contents is dense but genuinely useful for setting expectations, so nothing reads as filler.

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?

With no output schema, the description steps up by describing what is written to disk and that the return reports each file's purpose. Preconditions (finished run, empty folder) and the overwrite escape hatch are covered; only the absence of explicit sibling routing keeps it short of complete.

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 coverage is already 100%, so baseline is 3, and the description adds real meaning on top: it explains the refusal semantics of overwrite (file replacement is blocked by a non-empty folder) and frames folder as 'where to unpack into the project'. run_id gains the 'finished/passed' precondition, which the schema hints at but the prose reinforces.

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?

Names a specific verb (download/unpack) and resource (a finished run's result), then enumerates exactly what lands in the project: the TFLite Micro model, C sources under c/, and the report. That content list makes it easy to distinguish from get_report or list_runs, though it never names an alternative tool.

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

Usage Guidelines3/5

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

'A finished run's result' implies the run must have completed, and the run_id schema description narrows it further to lossless/optimize runs that passed. However, there is no explicit statement of when to pick this over siblings such as get_report or run_status, so guidance remains implied rather than stated.

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