Skip to main content
Glama

follow

Follow a trading model (from the STARTER plan, starter-20): creates the follow record — the model, your sizing (fixed_notional usd, or proportional bps of your balance), your caps (max_notional_usd, max_open_positions, max_daily_loss_usd, markets) and optionally the wallet your own runner will sign with. Validated exactly as follow_quote; one active follow per model, a new one supersedes it. Returns the record, its digest (the coordination record follow.created) and the attribution every mirror of it is placed under (copy::). Nothing is traded by this call: your own runner mirrors fills under this record, and it can be stopped with unfollow at any time.

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": {
      "sizing": "<sizing>",
      "caps": "<caps>"
    },
    "name": "follow"
  }
}

Input Schema

NameRequiredDescriptionDefault
capsYes{"max_notional_usd":100,"max_open_positions":3,"max_daily_loss_usd":40,"markets":["BTC"]}
modelNothe model's attribution from the models tool (or give script instead)
scriptNoinstead of a model: a PROVEN script's id from the strategies tool (scripts.proven); followed through the desk that runs it, only while the gate lists it PROVEN and the desk trades live
sizingYes{"kind":"fixed_notional","usd":50} or {"kind":"proportional","bps":200}
follower_walletNothe 0x address your runner signs mirrors with (optional now; required once the venue enforces per-order auth)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / model / description
      Previous value: -"the model's attribution from the models tool"New value: +"the model's attribution from the models tool (or give script instead)"
    • addedInput schema / properties / script
      Added value: +{
      +  "description": "instead of a model: a PROVEN script's id from the strategies tool (scripts.proven); followed through the desk that runs it, only while the gate lists it PROVEN and the desk trades live",
      +  "type": "string"
      +}
    • changedInput schema / required
      Previous value: -[
      -  "model",
      -  "sizing",
      -  "caps"
      -]New value: +[
      +  "sizing",
      +  "caps"
      +]
  2. Added

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare readOnly=false, destructive=false, idempotent=false; the description adds the crucial context that nothing is traded on invocation, that a new follow supersedes the prior one (non-obvious mutation), and that a runner mirrors fills under the record. It also discloses the returned digest and attribution string. Not a 5 only because it doesn't address auth requirements or error/failure modes beyond passing validation to follow_quote.

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?

A single dense paragraph that front-loads the action and the record being created, then layers sizing, caps, and the no-trade clarification. Slightly long and packed with parentheticals, but essentially every clause carries information an agent needs.

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 mutation tool with no output schema, five params, and nested objects, the description covers the created record, its digest event, the attribution format, and the lifecycle (supersede, unfollow). Nothing essential to calling it correctly is missing.

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 baseline is 3, but the description genuinely adds meaning: it decodes sizing into fixed_notional usd versus proportional bps of balance, enumerates the cap fields in prose, and explains follower_wallet as the address the caller's own runner signs with. That is more than the schema's raw examples.

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?

Opens with a specific verb+resource ("Follow a trading model") and immediately names the plan scope (STARTER, starter-20). It distinguishes itself from follow_quote by stating "Validated exactly as follow_quote" and from unfollow by naming it as the stop mechanism, so an agent can place it among siblings without opening schemas.

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 explicit when-to-use context (follow a model, or a PROVEN script's id), the alternative validation path (follow_quote), the exclusivity rule ("one active follow per model, a new one supersedes it"), and the exit path (unfollow). That is when, when-not-redundant, and alternative in one paragraph.

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