OneQAZ Trading Intelligence

get_llm_trading_decisions

Read-onlyIdempotent

Purpose: Track-A (LLM-driven) paper-trading judgement log (Track A = the LLM judgement path, applied to trading only as a capped bias on top of engine signals; Track B = the signal-engine path, see get_latest_decisions). Triggers (casual questions too): "what does the AI think?", "AI는 뭘 사라고 해?", "show the LLM's trade calls", "AI 판단 근거 보여줘", "does the AI agree with the signals?". When to call: inspect LLM-generated reasoning and trade calls. Prerequisites: none. Next steps: get_latest_decisions to compare with Track B. Caveats: paper-trading only.

Args: market_id: Market ID (crypto, kr_stock, us_stock, commodity, forex, bond) symbol: Specific symbol (optional; omit for entire market)

Disclaimer: Information only, not investment advice.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`symbol`	No
`market_id`	Yes

Output Schema

TableJSON Schema

Name	Required	Description
`error`	No	Set true on error responses
`action`	No	Recommended client action (error path)
`reason`	No	Human-readable cause (error path)
`full_data`	No
`retryable`	No	Whether the client should retry (error path)
`timestamp`	Yes	RFC3339 UTC, server build time
`ai_summary`	No	One-line AI-oriented summary (success path)
`disclaimer`	Yes	Canonical compliance disclaimer (always present)
`error_code`	No	Stable error identifier; see mcp_error_policy.md
`request_id`	Yes	32-hex per-response correlation id
`_llm_summary`	No
`action_value`	No
`_next_actions`	No
`fallback_note`	No
`fallback_tool`	No	Suggested fallback (error path)
`is_real_money`	No
`_value_signals`	No
`summary_for_user`	No	One-line jargon-free Korean summary (success path)
`data_classification`	No
`is_investment_advice`	No
`ai_summary_ttl_seconds`	No
`_market_state_narrative`	No
`ai_summary_generated_at`	No	RFC3339 UTC
`_followup_questions_for_user`	No

TDQS

A4.8/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, so the description adds valuable context beyond them: the tool is paper-trading only, and the LLM judgement is a 'capped bias on top of engine signals'. This provides behavioral nuance without contradicting annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Structured with clear headers (Purpose, Triggers, When to call, Prerequisites, Next steps, Caveats, Args, Disclaimer) and front-loaded with the purpose. Every section adds functional value, including the multilingual trigger examples, without redundancy.

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?

The description covers purpose, usage context, exclusions, parameter semantics, and caveats, while the output schema and annotations handle return types and safety profile. It is fully complete for an agent to select and invoke correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema has no descriptions (0% coverage), but the description fully compensates by defining market_id with allowed values (crypto, kr_stock, us_stock, commodity, forex, bond) and explaining symbol as optional and market-scoping. This is exactly the semantic detail an agent needs.

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 explicitly states 'Purpose: Track-A (LLM-driven) paper-trading judgement log' and differentiates Track A from Track B (signal-engine path) by referencing get_latest_decisions. It clearly identifies the verb (get/inspect) and resource (LLM-generated trading decisions).

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?

Provides explicit 'When to call' guidance ('inspect LLM-generated reasoning and trade calls'), prerequisites ('none'), and next steps ('get_latest_decisions to compare with Track B'), directly addressing when to use this tool versus the sibling alternative.

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

All OneQAZ Trading Intelligence tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.3/5.0

Disambiguation4/5

Most tools have clearly distinct purposes, but there are overlapping areas such as get_feature_governance_state vs get_feature_governance_status_tool and the convenience wrappers for losing/winning positions/trades. Descriptions clarify relationships well, so confusion is limited.

Naming Consistency4/5

The vast majority follow a consistent 'get_' prefix with descriptive nouns, but inconsistencies exist: some tools have '_tool' suffix (e.g., get_macro_causality_graph_tool) while similar ones do not, and governance tools use 'state' vs 'status_tool'. Overall, the pattern is predictable.

Tool Count2/5

39 tools is excessive for the apparent scope. Many are redundant convenience wrappers (get_losing_positions, get_winning_trades, etc.) that duplicate filters on other tools, and there are near-duplicate governance tools. The count could be significantly consolidated.

Completeness5/5

The tool surface is remarkably comprehensive, covering signals, trades, predictions, positions, macro relationships, news causality, strategies, structure, governance, and ledger integrity. There are no obvious functional gaps, and the tools form a well-integrated evidence chain.

get_llm_trading_decisions

Input Schema

Output Schema

TDQS

Glama MCP Gateway

TDQS

Resources