Skip to main content
Glama
Sign In
pathiel

pathiel

by Julian-dev28
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

get_desk_record

Judge whether a trading desk's calls deserve trust by reading its graded track record: hit rate, Brier score, mean return, and trades taken. Set grade=true to grade expired calls first.

Instructions

Get a desk's graded track record: calls graded, direction hit rate, mean Brier score, mean return, results by outcome, machine calls vs the user's own, and trades taken against each call. grade=true first grades expired calls and closed trades (writes the local journal, places no order); use it when calls have expired since the last grading, else leave it off and read. Use to judge whether a desk's calls deserve trust; for the current call use get_desk_brief. A desk with nothing graded yet returns n_graded 0. Returns {desk, track_record}, or {graded, record} with grade=true.

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_record"
  }
}

Input Schema

NameRequiredDescriptionDefault
deskYesDesk id from list_desks (oil, metals, ...).
gradeNoGrade expired calls and trades before reading.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.6.1

TDQS

A4.5/5.0
Behavior4/5

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

Goes well beyond the lone destructiveHint=false annotation by disclosing that grade=true writes the local journal while placing no order, and by stating the empty-state behavior (n_graded 0). What remains unstated is failure behavior for a bad desk id or the cost/latency of grading, which keeps it short of a 5.

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?

Front-loaded with the payload contents, then the grading caveat, then usage routing. Dense with no obvious filler, though the trailing 'Returns {desk, track_record}, or {graded, record} with grade=true' fragment is terse enough to read as an afterthought.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

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 the return-value burden and does list the metrics plus both response shapes and the empty case. It stops short of field-level detail for each metric, but an agent can call it correctly from what is given.

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 the baseline is 3, but the description adds real meaning to grade: not just 'grade first' but what it writes (local journal), what it does not do (no order), and when to enable it. The desk parameter is left to the schema, which already sources it from list_desks.

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?

Names a specific verb and resource and then enumerates exactly what the record contains (calls graded, hit rate, Brier score, mean return, by-outcome breakdown, machine vs user calls, trades per call). It also explicitly separates itself from get_desk_brief, so an agent can pick the right tool 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?

Gives explicit when-to-use framing ('Use to judge whether a desk's calls deserve trust'), the condition for the optional flag ('use it when calls have expired since the last grading, else leave it off and read'), and a named alternative for the adjacent need ('for the current call use get_desk_brief').

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