Skip to main content
Glama

Start a study

create_study

Opens a study, the named set of runs every backtest belongs to: call it once per question, before run_backtest. Can set a hold-out period, once and only here, that no run tests except run_held_out_test. Only the first held-out test per account and market counts, and any earlier run on the market (in any study, at any bar size) that read its days disqualifies it: set the hold-out in your first study on a market, before any run on it.

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": {
      "name": "<name>"
    },
    "name": "create_study"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesWhat the study tests, in a few words.
hold_outNoThe days kept back from every run but run_held_out_test; set once, here. Set it in your first study on a market, before any run on it: a held-out test on days an earlier run on the market read does not count.

Output Schema

NameRequiredDescriptionDefault
nextNo
reasonNo
statusYes
messageNo
hold_outNo
study_idNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / hold_out / description
      Previous value: -"The days kept back from every run but run_held_out_test; set once, here."New value: +"The days kept back from every run but run_held_out_test; set once, here. Set it in your first study on a market, before any run on it: a held-out test on days an earlier run on the market read does not count."
  2. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations cover safety (destructive=false) but say nothing about the domain constraints the description supplies: the hold-out is settable once and only here, only the first held-out test per account/market counts, and prior runs on the market poison it. That is substantial non-obvious behavior. The gap is that 'opens' is soft for a write operation and nothing is said about re-calling with an existing name, despite idempotentHint=false.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose and the before-run_backtest instruction are correctly front-loaded, and there is no filler. But the final sentence is a comma-spliced chain that restates the 'set once, here' constraint already given a sentence earlier and in the schema, making the hold-out rule harder to parse than it needs to be.

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?

With only two parameters, a 100% covered schema, an output schema (so return values need no explaining) and a nested hold_out object fully described, everything an agent needs to call this correctly — purpose, ordering, and the hold-out eligibility rule — is present.

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 100%, so both parameters are already documented, including the YYYY-MM-DD patterns; baseline would be 3. The description still adds value by tying hold_out to run_held_out_test and to the ordering constraint against prior runs on a market, context the schema cannot express.

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?

The description gives a specific verb and resource ('Opens a study') and immediately defines what a study is ('the named set of runs every backtest belongs to'), which no schema field does. It also names the sibling it must precede (run_backtest), so an agent can place it relative to run_backtest and run_held_out_test without opening either 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?

Explicit sequencing guidance: 'call it once per question, before run_backtest' tells the agent both frequency and ordering. It also names the exact precondition for the hold-out option and the disqualifying condition ('any earlier run on the market ... that read its days disqualifies it'), which is a concrete when-to-use/when-not rule rather than an inference.

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