Skip to main content
Glama

Fine-tune data formatter

submit_fine_tune_data_formatter
Idempotent

Convert raw instruction/response pairs into training JSONL in chat or completion format. When preparing labelled pairs for a fine-tuning run. Do not choose this when you need data quality judged, which needs a model. Example requests: Format these pairs for fine-tuning. | Convert my instruction/response data to training JSONL. | Prepare this dataset in chat format.

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": {
      "inputs": "<inputs>",
      "authorized_by": "<authorized_by>"
    },
    "name": "submit_fine_tune_data_formatter"
  }
}

Input Schema

NameRequiredDescriptionDefault
inputsYes
quote_idNoThe quote_id returned by POST /v1/jobs. Required to authorize a priced capability; the service rejects a priced job that does not name the quote it issued.
authorized_byYesIdentifier of the human or agent authorizing this job.
accepted_priceNoThe amount accepted, exactly as quoted (for example "5.00" or 5). Checked against the stored quote, so a price that moved between quote and authorize is refused rather than silently absorbed. Optional, but sent to make the acceptance explicit.

Output Schema

NameRequiredDescriptionDefault
quoteNo
stateYes
job_idYes
artifactsNo
access_tokenNoPer-job credential. Present it as the X-Job-Token header to read the job or list it. Keep it; it is the only credential for this job.
verificationNoIndependent verification. verification.ok = false means the job failed, not a partial success.
capability_idNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already declare idempotent, non-destructive, non-open-world behavior, so the safety profile is covered. However, the description omits that this is a priced capability requiring quote_id and authorized_by, which is material to invocation, and says nothing about size or processing characteristics beyond a byte cap already in the schema.

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?

Purpose is front-loaded in the first sentence, followed by usage and exclusions. The sentence fragment 'When preparing labelled pairs for a fine-tuning run.' is awkward, and the three example requests are somewhat redundant with the opening sentence, but nothing is seriously bloated.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists so return values need no explanation, and the nested input shape is documented in-schema. The gap is the commercial workflow: with quote_id, authorized_by, and accepted_price in the schema, an agent reading only the description would not know a quote must be obtained first or that the price is validated against a stored quote.

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 75% and the nested schema already documents raw_pairs (CSV text) and target_format (chat or completion) in detail. The description adds no format syntax, quoting, or validation guidance beyond restating 'chat or completion', so it stays at the baseline.

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 and resource ('Convert raw instruction/response pairs into training JSONL') plus the two output modes (chat or completion). The explicit contrast with quality-judging work separates it from the many quality/report siblings in a crowded toolset.

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 both a positive trigger ('When preparing labelled pairs for a fine-tuning run') and a negative one ('Do not choose this when you need data quality judged, which needs a model'). It stops short of naming the concrete alternative (e.g. submit_dataset_quality_report), so an agent must map the exclusion itself.

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