get_historical_levelsReplay key options levels (gamma flip, call/put walls, highest OI strike, 0DTE magnet) at any minute since April 2018. Alpha tier.
| Name | Required | Description | Default |
|---|---|---|---|
| at | Yes | As-of timestamp: YYYY-MM-DDTHH:mm:ss (ET) or YYYY-MM-DD | |
| apiKey | No | FlashAlpha API key. Omit when calling via /mcp-oauth (OAuth flow); required on /mcp. | |
| symbol | Yes | Stock/ETF ticker |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already declare readOnlyHint=true, so the safe-read nature is known. The description adds useful context: data availability since April 2018, minute-level replay, and the specific level types returned. However, it does not describe output shape, pagination, or behavior when no data exists at a timestamp.
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 two concise sentences with no filler. The first sentence front-loads the core purpose and content, and 'Alpha tier' is a brief but meaningful access signal.
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-only historical lookup, the description conveys data type, granularity, and date range, which is sufficient for an agent to understand the tool's scope. It omits output format, but the absence of an output schema and the clear parameter schema keep it reasonably complete, though it could clarify snapshot semantics for the 'at' timestamp.
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 100%, with clear descriptions for symbol, at, and apiKey in the input schema. The description does not add parameter-level syntax or format details beyond what the schema already provides, so the baseline score of 3 applies.
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 identifies the tool as replaying historical key options levels, with a specific verb ('Replay') and a concrete list of included levels (gamma flip, call/put walls, highest OI strike, 0DTE magnet). This distinguishes it from siblings like get_levels (current levels) and other historical_* tools.
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?
There is no explicit guidance on when to use this tool versus alternatives, such as saying 'use for historical data; for current levels use get_levels'. The description only notes historical depth and 'Alpha tier', which hints at access but not usage context or exclusions.
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.
Many tools have overlapping scopes: get_stock_summary, get_volatility, get_vrp, and get_exposure_summary all return comprehensive analytics with shared metrics, making it hard to pick the right one. The flow family (get_flow_live, get_flow_summary, get_flow_scan, get_flow_signals, etc.) has significant redundancy — get_flow_live bundles data also available via separate tools.
Tool names mostly follow a consistent get_<noun> pattern, with clear subgroups like get_historical_* and get_*_exposure. Minor deviations exist: post_screener, post_structure_pnl, calculate_greeks, and solve_iv break the get_ convention, but they are still predictable and readable.
With 73 tools, this is far beyond the 3–15 tool sweet spot and even the 50+ extreme mismatch threshold. While the domain is broad, the enormous surface is bloated by near-duplicate historical replay variants (18 get_historical_* tools) and multiple overlapping summary endpoints, making it unwieldy for an agent.
The tool set provides thorough coverage of options analytics: quotes, chains, greeks, volatility surface, VRP, exposure, flow, historical replay, screening, and strategy analysis. There are no obvious dead ends — core workflows like calculating greeks, getting exposure, and screening the universe are all supported.