Skip to main content
Glama

OptionsBell Options Flow

by com.optionsbell
OverviewDiscussionsAdmin

Open-interest changes (Pro)

get_oi_changes

Day-over-day open-interest change per symbol (total, calls, puts) - fresh positioning being built or unwound. Pass a symbol for its OI-change series (date_from, date_to, limit apply); omit it for market-wide gainers/losers.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dateNoTrading day, YYYY-MM-DD. Defaults to the latest available day.
sideNoMarket-wide view only.
limitNo
offsetNoMarket-wide view only. Rows to skip for paging; the response reports filtered_total and has_more.
symbolNoSingle ticker for its OI-change series; omit for the market-wide view.
date_toNoRange end, YYYY-MM-DD inclusive.
symbolsNoComma-separated tickers, e.g. 'AAPL,NVDA,TSLA'.
date_fromNoRange start, YYYY-MM-DD inclusive.
min_prev_oiNoMinimum prior-day OI to filter low-base noise (default 1000; market-wide only).
min_change_pctNoMinimum absolute day-over-day change, e.g. 0.5 = 50% (market-wide only).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / offset
      Added value: +{
+  "description": "Market-wide view only. Rows to skip for paging; the response reports filtered_total and has_more.",
+  "maximum": 9007199254740991,
+  "minimum": 0,
+  "type": "integer"
+}
  2. Changed7 schema fields changed
    • addedInput schema / properties / date_from
      Added value: +{
+  "description": "Range start, YYYY-MM-DD inclusive.",
+  "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
+  "type": "string"
+}
    • addedInput schema / properties / date_to
      Added value: +{
+  "description": "Range end, YYYY-MM-DD inclusive.",
+  "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
+  "type": "string"
+}
    • changedInput schema / properties / min_change_pct / description
      Previous value: -"Minimum absolute day-over-day change, e.g. 0.5 = 50%."New value: +"Minimum absolute day-over-day change, e.g. 0.5 = 50% (market-wide only)."
    • changedInput schema / properties / min_prev_oi / description
      Previous value: -"Minimum prior-day OI to filter low-base noise (default 1000)."New value: +"Minimum prior-day OI to filter low-base noise (default 1000; market-wide only)."
    • addedInput schema / properties / side / description
      Added value: +"Market-wide view only."
    • changedInput schema / properties / side / enum
      Previous value: -[
-  "gainers",
-  "losers"
-]New value: +[
+  "gainers",
+  "losers",
+  "all"
+]
    • addedInput schema / properties / symbols
      Added value: +{
+  "description": "Comma-separated tickers, e.g. 'AAPL,NVDA,TSLA'.",
+  "type": "string"
+}
  3. First observed

TDQS

A4/5.0
Behavior3/5

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

With no annotations, the description carries the behavioral disclosure burden. It does convey the day-over-day computation, per-symbol vs market-wide behavior, and the interpretive meaning of 'fresh positioning being built or unwound.' However, it does not describe return shape, sorting semantics, or pagination beyond what the schema mentions, so some behavioral context is left implicit.

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?

The description is two compact sentences with no filler. The core concept is front-loaded, and the mode-switching instruction is placed immediately afterward, making it quick to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 10-parameter tool with no annotations and no output schema, the description plus rich schema coverage is largely sufficient. It explains the two main usage modes and the supported fields, while the schema fills in defaults, bounds, and market-wide-only constraints. A return-format hint would improve completeness slightly, but the current combination is adequate.

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

Parameters3/5

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

Schema description coverage is 90%, so the schema already documents nearly all parameters. The description adds useful framing about which parameters apply in which mode ('date_from, date_to, limit apply' for symbol mode; omit symbol for market-wide), but it does not add substantial semantics beyond the schema for most parameters.

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 names a specific resource ('Day-over-day open-interest change per symbol') with explicit components (total, calls, puts) and a clear verb. It also distinguishes the two operating modes by symbol vs market-wide, making it easy to tell apart from sibling flow and IV tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives direct invocation guidance: pass a symbol for an OI-change series, omit it for market-wide gainers/losers. It does not explicitly name alternative sibling tools or state when not to use this tool, but the mode-based usage is clear enough for an agent to choose correctly.

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

All OptionsBell Options Flow toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources