Realized trading performance for an agent, derived from position_closed events: trade count, win rate, total/average P&L (bps), total P&L (USD), average holding hours, per-ticker breakdown and the last 20 closed trades. agent: gap-trader | narrative-trader. mode: '' (all) | paper | live | onchain — filter trades by execution mode.
| Name | Required | Description | Default |
|---|---|---|---|
| days | No | ||
| mode | No | ||
| agent | No | gap-trader |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, so the read-only nature is known. The description adds behavioral context by specifying the derivation from position_closed events, inclusion of a per-ticker breakdown, and the last 20 closed trades, which goes beyond the annotations. No contradiction with annotations.
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?
The description is compact, using two sentences to convey output metrics and parameter filtering. The first sentence is list-heavy but front-loaded with the core purpose. There is no repetition of trivial details, though the structure could be slightly clearer with bullet points.
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?
With no output schema, the description lists the main returned metrics, which is essential. However, it omits the meaning of the days parameter, default behaviors, and any caveats about data freshness or limitations. For a simple read-only analytics tool, it is adequate but has clear gaps.
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?
The schema has 0% description coverage, leaving all three parameters undocumented. The description compensates well for agent and mode by explaining their allowed values, but entirely omits days, whose purpose as a lookback period is only inferred from its default value of 30. Thus partial compensation.
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 the tool returns realized trading performance metrics for an agent, derived from position_closed events, listing specific outputs (trade count, win rate, P&L, holding hours, ticker breakdown, last 20 trades). This distinguishes it from sibling tools like gap_trade_signals or competition_my_portfolio by focusing on completed agent trades.
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?
The description provides allowed values for agent (gap-trader | narrative-trader) and mode ('' | paper | live | onchain), implicitly telling users how to filter. However, it does not explicitly state when to use this tool versus alternative performance-related tools, nor mention any exclusions or prerequisites.
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.
Most tools have clearly distinct purposes, with detailed descriptions that separate e.g. hood_basis_snapshot from hood_basis_history and perp_spot_basis. A few clusters like flow_summary vs token_flows and multiple gap/basis tools could still cause slight ambiguity, but the descriptions are strong enough to guide correct selection.
All tool names follow a consistent snake_case pattern with domain prefixes (hood_, agent_, competition_, partner_), and verbs are used predictably (report_, execute_, get_, etc.). There is no mixing of conventions or vague generic names.
39 tools is on the high side, but the server covers a very broad domain (market data, signals, trading execution, competition, partner APIs, agent reporting). While many tools earn their place, a few could be consolidated (e.g., gap/basis variants), making it feel heavier than necessary for typical usage.
The surface covers the core lifecycle: market data, signals, paper/real/partner trading, position tracking, and performance reporting. Minor gaps exist (e.g., no explicit wallet balance or order cancellation), but the core workflows are well-covered and derived endpoints fill most needs.
