Skip to main content
Glama

BotSpot: AI Trading, Backtests and Bots

Strategies and charts open in this conversation

conversation_attachments

A conversation can hold several strategies and charts. action="list" shows what is attached and which strategy is primary; action="attach" adds one of the person’s strategies (kind="strategy") or charts (kind="chart") by refId, and attaching a strategy makes it primary; action="detach" removes one by attachmentId without deleting it. When the person says "this strategy" and several are attached, ask which one unless one is clearly selected.

Set "action" to choose the operation. Only send the fields listed for that action.

action="list": List what is open in this conversation

No other fields required. Lists the strategies and charts attached to this conversation, with which strategy is primary. When the person says "this strategy" and more than one strategy is attached, ask which one unless one is clearly selected.

action="attach": Attach a strategy or chart

Required fields: kind, refId. Attaches one of the person’s strategies or charts to this conversation. Attaching a strategy makes it the primary strategy, like switch_active_strategy.

action="detach": Remove a strategy or chart from this conversation

Required fields: attachmentId. Removes one attachment from this conversation without deleting the strategy or chart. The only strategy cannot be removed; attach another first.

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": {
      "action": "<action>"
    },
    "name": "conversation_attachments"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNoWhat to attach. Used with action="attach". Required for action="attach".
refIdNoStrategy id (strategyId or aiStrategyId) or chart id (chartId). Used with action="attach". Required for action="attach".
actionYesWhich operation to run: "list", "attach", "detach". See the tool description for each one.
attachmentIdNoAttachment id from action="list". Used with action="detach". Required for action="detach".
conversationIdNoLeave empty to use the current conversation. Used with action="list", action="attach", action="detach".

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior5/5

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

Annotations declare a non-read-only, non-idempotent, non-destructive operation; the description adds the concrete consequences: attaching a strategy makes it primary (a state change beyond simple attachment), detaching removes the attachment without deleting the strategy or chart, and the last remaining strategy cannot be removed until another is attached. These constraints go well beyond what the annotations convey and prevent predictable agent errors.

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?

Good front-loading: the opening paragraph summarizes all three actions, then each is expanded under a heading with required fields. There is redundancy — the "this strategy" ambiguity rule appears both in the intro and again under action="list" — which costs a point but does not obscure the content.

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?

For a five-parameter, conditionally-required tool with no output schema, the description supplies everything needed: the action model, required fields per action, default behavior for conversationId implied by the schema, and the key business rules (primary promotion, non-deleting detach, last-strategy restriction). Nothing material is missing for correct invocation.

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 100%, so every parameter already carries a description tying it to an action, including refId accepting strategyId/aiStrategyId/chartId. The description mostly restates the per-action required-field mapping ("Only send the fields listed for that action") rather than adding new meaning, so baseline 3 applies.

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 names the specific resource (strategies and charts attached to a conversation) and enumerates three concrete operations with verbs (list, attach, detach), plus the exact fields each uses. An agent can distinguish this from siblings like switch_active_strategy or get_strategy 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 Guidelines4/5

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

Guidance is explicit per action: use list to see what is open and which strategy is primary, attach to bring in one of the person's strategies/charts, detach to remove an attachment without deleting the underlying object. It also gives a disambiguation rule: when the person says "this strategy" and several are attached, ask which one unless one is clearly selected. It does not state when to prefer switch_active_strategy over attach, only that they are analogous, so it falls short of full alternatives coverage.

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.