SwishrJobs

Backtest overfitting check

submit_backtest_overfitting_check

Idempotent

Measure the decay from in-sample to out-of-sample performance and flag parameter-rich strategies. After a backtest, before trusting its in-sample performance. Do not choose this when a full statistical overfitting test is required. Example requests: Check this backtest for overfitting. | How much performance does this strategy lose out of sample? | Flag the overfitting risk in these results.

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_backtest_overfitting_check"
  }
}

Input Schema

Name	Required	Description
`inputs`	Yes
`quote_id`	No	The 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_by`	Yes	Identifier of the human or agent authorizing this job.
`accepted_price`	No	The 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

Name	Required	Description
`quote`	No
`state`	Yes
`job_id`	Yes
`artifacts`	No
`access_token`	No	Per-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.
`verification`	No	Independent verification. verification.ok = false means the job failed, not a partial success.
`capability_id`	No

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 3, 2026

TDQS

A4.2/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=true and openWorldHint=false, so the safety profile is covered. The description adds the analytical behavior (decay measurement, risk flagging) but says nothing about the priced-job lifecycle implied by quote_id/authorized_by/accepted_price — no mention that the call consumes a quote, may be rejected on a stale price, or how the submitted job is fulfilled. That is a real disclosure gap for a non-read-only submission tool.

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?

Four compact segments: capability statement, timing, exclusion, then example utterances. Each earns its place and the purpose is front-loaded before the usage constraints. No redundant restatement of the title.

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?

An output schema exists, so return values needn't be explained, and the nested input schema is well documented. What is missing is the surrounding workflow — that a quote must be obtained (via preflight_job / POST /v1/jobs) before authorization succeeds — which an agent would need to call this correctly on the first try.

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 description coverage is 75%, and the nested inputs.results field already documents the accepted CSV format, header requirement, and 1 MiB cap, so the baseline of 3 applies. The description adds no parameter-level meaning at all — nothing about what 'results' must contain to span in-sample vs out-of-sample, and nothing distinguishing quote_id from accepted_price.

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 analytical verb pair — measure in-sample to out-of-sample decay and flag parameter-rich strategies — and names the boundary against the heavier alternative ('a full statistical overfitting test'). An agent can distinguish this from submit_job or other backtest-adjacent siblings without opening the schema.

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

Usage Guidelines5/5

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

Gives both the trigger ('After a backtest, before trusting its in-sample performance') and an explicit exclusion ('Do not choose this when a full statistical overfitting test is required'), plus three example requests that map natural-language phrasings onto the tool. This is the strongest section of the definition.

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

All SwishrJobs tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?