Skip to main content
Glama
Sign In
pathiel

pathiel

by Julian-dev28
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

get_desk_brief

Read-only

Fetches a trading desk's current call (side, entry, stop, targets) plus the position size your risk profile supports. Use before placing a desk trade.

Instructions

Get one desk's current trade call to trade from: side, entry, stop and targets, the reasoning, and your_size, the size this account would take at those levels under its risk profile and desk share. mode=quick (default) is short markdown with the call first; mode=full adds the evidence (news, levels, scenarios). stale lists what is out of date; when the thesis is stale or its target was hit, call refresh_desk. Use before placing a desk trade with place_bracket. Not for the desk's past accuracy (get_desk_record) or the list of desks (list_desks). Read-only; needs no key. An unknown desk id returns {error: no such desk}. Returns {desk, mode, markdown, your_size: {side, size, notional_usd, leverage, margin_usd}, stale[]}.

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": {
      "desk": "<desk>"
    },
    "name": "get_desk_brief"
  }
}

Input Schema

NameRequiredDescriptionDefault
deskYesDesk id from list_desks (oil, metals, ...).
modeNoquick (default): short markdown, the call first. full: adds the evidence.quick

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.6.1

TDQS

A4.4/5.0
Behavior3/5

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

Annotations only declare readOnlyHint=true, and the description confirms 'Read-only; needs no key' plus error behavior for an unknown desk id, which is genuine added context. However, much of the remaining content restates the return shape rather than disclosing traits like latency, caching, or freshness semantics beyond the 'stale' field.

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?

Content is dense and mostly front-loaded — the call-first sentence is the right lead. The remainder is a long semicolon-chained run-on mixing mode semantics, sibling routing, and return shape, which costs some scannability though little is truly wasted.

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 no output schema, the description carries return-value burden and does so, listing the response keys including the nested your_size fields and stale[]. It also covers the error case, leaving nothing an agent needs before invoking it.

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; the description earns an extra point by explaining what 'full' actually adds (news, levels, scenarios) versus quick's call-first markdown, which helps the agent choose a mode. The 'stale' sentence ambiguously reads like a parameter when it is a returned field, slightly muddying param mapping.

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 leads with a specific verb and resource ('Get one desk's current trade call') and immediately enumerates what that object contains (side, entry, stop, targets, reasoning, your_size). It also distinguishes itself from specific siblings (get_desk_record, list_desks, refresh_desk), so an agent can pick it without inspecting other tools.

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?

It gives explicit when-to-use ('Use before placing a desk trade with place_bracket'), explicit when-not ('Not for the desk's past accuracy ... or the list of desks'), and a concrete handoff condition to a sibling ('when the thesis is stale or its target was hit, call refresh_desk'). This is the full when/when-not/alternative triangle.

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

Deploy Server

Other Tools