Fetch the bundled critical skill pack (regime + risk_calendar + health). Call this on every boot before any trading decisions. Returns the current market regime, known risk events in the next 14 days, and a market health score — three synthesised verdicts that every strategy depends on.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses that the tool returns three synthesized verdicts (market regime, risk events, health score). With no annotations provided, the description adequately conveys the tool's behavior as a read operation, though it could mention data freshness or caching.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences: first explains purpose and recommended usage, second lists return values. Every word earns its place; no fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and no annotations, the description provides sufficient context: what the tool returns and when to invoke. Could be enhanced by noting error conditions or response format, but adequate for a simple fetch.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has zero parameters and schema coverage is 100%, so the description correctly contains no parameter details. Baseline of 4 applies as the description adds no redundant information.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it fetches the 'bundled critical skill pack' composed of regime, risk_calendar, and health. It uses a specific verb 'Fetch' and identifies the resource as a bundle, distinguishing it from the sibling 'get_skill' which likely returns a single skill.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly advises calling 'on every boot before any trading decisions', providing strong usage context. No explicit alternatives or exclusions are given, but the directive covers when to use the tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct function: trade recording, status checking, alerts, skills, ticker briefs, findings, voting, etc. No two tools have overlapping purposes; even add_trade and submit_trade are clearly separated by context (attaching to a finding vs. raw submission).
Tool names follow a verb_noun pattern in snake_case (e.g., get_skills, publish_finding). However, add_trade and submit_trade use different verbs for similar actions, and there are multiple get_ prefixes, but overall the pattern is consistent and predictable.
11 tools is a well-scoped set for a trading intelligence network. Each tool serves a clear purpose, covering status, findings, trades, alerts, skills, and network briefs without being overwhelming or too sparse.
The tool set covers the core workflows: publishing and querying findings, submitting trades, voting, checking status and alerts. Minor gaps exist (e.g., no tool to update or delete a finding/trade), but the surface is largely complete for the intended domain.