Skip to main content
Glama

BotSpot: AI Trading, Backtests and Bots

Replace a strategy file

replace_file
Destructive

Replaces the full contents of an existing strategy file in a new immutable revision for any strategy owned by the authenticated user. Requires editHandle from get_file/list_files. Use this for first-build main.py replacement after create_strategy returns neutral starter files. For the current attached/open strategy, omit strategyId and revisionId after get_file; the server resolves the latest conversation revision, so do not manually transcribe those UUIDs. Pass explicit ids only for a named or different strategy. For existing-strategy fixes, this is the action step after get_file identified the concrete change and returned an editHandle. Mutate only the strategy/revision named by the user when it differs from the open page context. After a successful replace, call get_file on the returned new revisionId to read back the final saved code and verify the saved executable code before final-answering; do not verify by re-reading the original/base revisionId from before the edit. When an edit follows a backtest request or result in the same conversation, validate the new saved revision with the established window, capital and data settings after readback, even when the earlier run succeeded and the customer did not repeat the test request. Explicit save-only instructions and disabled automatic-backtest preferences take precedence. A standalone file edit without a backtesting workflow is complete after saving and readback unless testing was requested. Never deploy or trade merely to validate an edit. A successful mutation, compiling/ready analysis, or readback alone does not complete the requested repair. If the saved executable code still uses the faulty causal path the user asked to repair, or new helpers/scaffolding are not connected to it, continue the remaining authorized file edits with the current editHandle. Do not final-answer with a plan, apology, model-upgrade suggestion, or admission that the repair is incomplete while authorization and execution budget permit, the file tools work, and the remaining corrective edit is known. Recover ambiguous anchors with the returned unique context, an exact guarded range, or complete replace_file; a recoverable patch-format error is not a missing capability. Finish the requested change and preserve unrelated behavior and files. For copy/apply-same-rules requests, do not use replace_file after reading only one strategy, and do not use it after reading only the target. A different revision of the named target is still target evidence, not source evidence, unless the user explicitly asked to copy from an older target revision. First read the source strategy code and the named target strategy code, then diff executable assignments/thresholds/cadence/branches within the requested copy scope. Copy only explicitly requested mechanics for a limited transfer; update every differing target value to the source value only for whole-strategy parity. Preserve target-specific identity such as symbol/ticker, strategy name, account/broker identity, and labels unless the user explicitly asks to change them; do not copy the source symbol/name into the target. Build the replacement from the target file and selectively copy behavior values into it; do not replace the named target wholesale with the source file when identities differ. In Python strategy code, self.symbol is target identity when source and target tickers differ; for a TQQQ source applied to an SQQQ target, keep self.symbol as SQQQ while copying behavior rules. Target identity does not include cadence, sleeptime, trigger thresholds, order sizing, entry/exit branches, helper calls, or risk rules; those are behavior and must match the source only when included in the requested copy scope. Do not add settings absent from the source or merge unrelated memory/preferences. Before replace_file in a copy/apply-same-rules edit, preserve the literal target identity line from the target readback in the replacement content. If your replacement would turn target identity into source identity, do not call this tool yet; correct the replacement first. After readback for a copy/apply-same-rules edit, if the target file contains source identity such as the source symbol/name/account/broker, edit again before final-answering. Do not list source identity as evidence of success. When the fix replaces an executable setting, guard, helper call, order path, or branch, remove or replace the stale executable code; do not append a competing line and leave the old contradictory behavior in place. When the user says to stop using a value/source, or says that value/source is stale or wrong, remove executable fallback uses of that value/source instead of keeping them as a backup path. If the readback still contains the stale executable value/source/fallback the user asked to remove, the edit is not complete; call patch_file or replace_file again before final-answering. If the user supplied a concrete replacement value for a code-owned setting such as cost basis, entry price, threshold, cadence, market, symbol, or helper path, replace the stale executable literal/path and read it back. For live fill/cost-basis fixes where live order tools fail but the user supplied a concrete bot-owned fill, record/use that exact fill value in executable state/code as the bootstrap latest verified bot-owned fill; do not add only an unset placeholder such as None. For plan-driven first-build work, make the visible implementation item in_progress with update_plan_item before using file tools so the user sees the current plan step while file work runs. If replace_file or patch_file fails, no new revision was created: read the current file/editHandle and retry with a valid edit before starting a backtest or ending the strategy build.

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": {
      "path": "<path>",
      "editHandle": "<editHandle>",
      "content": "<content>"
    },
    "name": "replace_file"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYes
contentYes
editHandleYesOpaque edit handle returned by list_files or get_file. It replaces raw hash copying while preserving stale-write protection.
revisionIdNoBase revision ID to snapshot from. Omit with strategyId for the current attached/open strategy.
strategyIdNoBase strategy id. Omit with revisionId for the current attached/open strategy so the server uses the conversation's latest saved revision.
descriptionNoShown to the customer as "How your strategy works". One or two plain sentences on what the strategy now does, e.g. "Buys Apple after a 5% drop in a day and sells at a 10% gain." Write for the customer, not an internal change note.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / description / description
      Added value: +"Shown to the customer as \"How your strategy works\". One or two plain sentences on what the strategy now does, e.g. \"Buys Apple after a 5% drop in a day and sells at a 10% gain.\" Write for the customer, not an internal change note."
  2. First observed

TDQS

A4.4/5.0
Behavior5/5

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

The annotations already declare destructive=true, readOnly=false, and idempotent=false, but the description adds substantial behavioral context: it creates a new immutable revision, requires an editHandle from get_file/list_files, preserves stale-write protection, and does not create a revision when the call fails. It also explains readback verification requirements and copy/identity constraints beyond the annotation coverage.

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

Conciseness2/5

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

The description is a massive wall of text that reads more like an operating policy than a tool definition. Although the first sentence is well front-loaded, the remaining content is highly repetitive and contains many workflow, validation, copy, identity, and error-handling rules that could be shortened or moved to system-level instructions. The size and lack of structure make it hard for an agent to extract the most important rules.

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?

Given the destructive nature of the tool, the absence of an output schema, and the complexity of revision handling and copy workflows, the description is more than complete. It covers save/readback verification, identity preservation, stale-code removal, error recovery, and first-build sequencing, leaving little unaddressed for an agent to call the tool correctly.

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 67%, so the schema already documents key parameters like editHandle, strategyId, revisionId, and the optional description. The tool description adds useful guidance about omitting strategyId and revisionId for the current open strategy and not manually transcribing UUIDs, but it does not explain path, content, or the description parameter. Its parameter guidance is meaningful but incomplete.

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 opening sentence states a specific verb and resource: it replaces the full contents of an existing strategy file in a new immutable revision for strategies owned by the authenticated user. It clearly distinguishes this from patch-style edits and names required inputs such as editHandle. An agent can identify the operation 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?

The description is extremely explicit about when to use replace_file, including first-build main.py replacement after create_strategy, fixes after get_file returns an editHandle, and copy/apply-same-rules workflows. It also states when to omit strategyId and revisionId, when to pass explicit ids, and what to do after save and readback. It names alternatives like patch_file and get_file and describes when those are relevant.

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.