Skip to main content
Glama
Sign In
pathiel

pathiel

by Julian-dev28
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

refresh_desk

Generates a new desk thesis using fresh market data, news, policy and odds, writing only to the local journal. Use when a brief is stale or its target was hit; places no orders.

Instructions

Write a NEW thesis for one desk: pulls fresh market data, news, policy and odds, then makes one local Claude Code call (about a minute, billed to the local Claude Code plan; needs the claude CLI on PATH, else it fails fast). A refresh already running for the desk is joined, not repeated; force=true refreshes even when the desk's data is still fresh. Writes only the local desk journal; places no order. Use when get_desk_brief says the thesis is stale or its target was hit; otherwise read the current call with get_desk_brief. Returns the new call or the error.

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": "refresh_desk"
  }
}

Input Schema

NameRequiredDescriptionDefault
deskYesDesk id from list_desks (oil, metals, ...).
forceNotrue: refresh even when a recent refresh exists.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.6.1

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only supply destructiveHint=false, and the description carries far more: roughly a minute runtime, billing to the local Claude Code plan, a hard dependency on the claude CLI with fail-fast behavior, and concurrency semantics (a running refresh for the desk is joined, not duplicated). It also scopes side effects precisely: writes only the local desk journal and places no order.

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 core action and free of filler, but the long semicolon-and-parenthesis chain packs billing, CLI, concurrency, and side-effect notes into very dense clauses. Every clause earns its place, though readability would improve if split.

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 closes the loop by stating it returns the new call or the error. For a two-parameter mutating local operation it covers cost, latency, prerequisites, failure mode, concurrency, and side effects — nothing an agent needs to decide or call correctly is missing.

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 both parameters are already documented, and the description largely restates the force semantics (refresh even when data is still fresh) rather than adding new meaning. The desk parameter's provenance (from list_desks) is repeated from the schema, so the baseline of 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?

States a specific verb and resource: "Write a NEW thesis for one desk," plus the inputs it draws on (market data, news, policy, odds). The capitalized NEW and the contrast with get_desk_brief make it distinguishable from the sibling that only reads an existing call.

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 an explicit trigger ("Use when get_desk_brief says the thesis is stale or its target was hit") and an explicit alternative ("otherwise read the current call with get_desk_brief"). It also explains the force-flag condition for overriding freshness, leaving no inference needed.

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