Open interest with per-row quality flags (verified archive + flagged bridge). tf=1h (default, full history) or tf=5m (archive-native 5-minute rows from 2020-09; ranged pulls, ~100k rows max per call).
| Name | Required | Description | Default |
|---|---|---|---|
| tf | No | ||
| end | No | ||
| start | No | ||
| symbol | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
There are no annotations, so the description carries the full behavioral disclosure burden. It provides useful details beyond the schema: per-row quality flags, verified archive versus flagged bridge data, the timeframe-dependent data vintage, and the ~100k row cap per call. It doesn't describe output structure, but the core behavioral constraints are surfaced.
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 a single dense sentence that front-loads the core resource and quality information, then packs the important timeframe, history, and row-limit details into a compact remainder. Every clause adds value and there is no filler.
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?
For a read-oriented data retrieval tool with 4 parameters and no output schema, the description covers the main usage distinctions and constraints. It could be more complete by stating the expected start/end formats and explicitly saying the response contains rows keyed by symbol and timestamp, but overall the essential calling guidance is present.
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?
Schema coverage is 0%, so the description must compensate. It meaningfully explains tf semantics and the row/range limits of 5m pulls. However, start and end are only weakly implied by 'ranged pulls', and symbol is not elaborated beyond its schema type, leaving some burden on the agent.
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 exposes open interest data and distinguishes two timeframe modes (1h vs 5m), which positions it as a specific data resource. It doesn't explicitly differentiate from sibling tools like get_bars or get_funding, but 'open interest' is self-identifying enough within the suite.
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 gives practical usage context: tf=1h is the default with full history, while tf=5m is archive-native and intended for ranged pulls with a maximum row cap. However, it never states when to prefer this tool over alternatives or provides explicit exclusions, leaving the when-to-use decision mostly implied.
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 clearly target a distinct data resource: bars, events, fundamentals, funding, open interest, order flow, and so on. A few adjacent tools like audit_my_data and validate_backtest_data, or get_market_pulse and get_regime_label, are somewhat similar, but their descriptions provide enough separation for an agent to choose correctly.
The dominant pattern is get_<data_type>, used consistently across most tools and all in lowercase snake_case. The non-get tools are mostly still readable verb-noun names like build_bundle and validate_backtest_data, though lookahead_check and survivorship_check are minor deviations.
With 22 tools, this is on the heavier side for a single MCP server, especially since many tools have fairly specialized data sources. Each tool is individually justifiable, but the overall surface is large and may push agents to spend extra work choosing among near-adjacent data options.
The server covers far more than plain OHLCV: it includes fundamentals, insider and institutional ownership, funding rates, open interest, order flow, events, context, regime labels, and backtest-quality validation. Minor missing areas like trade-by-trade quotes or a broader symbol catalog mechanism exist, but the common market-data workflows are very well supported.