BeliefState

Get options activity

get_options_activity

Retrieves retained options bars, flow aggregates and open interest for one ticker. Select activity_type, call/put right, expiration, strike and observation-date filters; returns typed instrument fields, OHLC, volume or open interest with units and source support. Open interest is a position measure; trading volume is a flow. Use explicit date/instrument filters for large histories; source-file order is not a globally sorted latest option chain. Current requests recheck stale mirror metadata; historical/pinned reads remain fixed. Continue with the returned snapshot, cutoff, filters and cursor or next_offset; partial scans are not proof of no matches. Uses account allowance or prepaid credit.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "ticker": "<ticker>",
      "context": "<context>",
      "llm_model": "<llm_model>"
    },
    "name": "get_options_activity"
  }
}

Input Schema

Name	Required	Description
`as_of`	No	Availability cutoff, separate from event/period filters. Historical reads never refresh.
`limit`	No	Matching typed observations per page; default32.
`right`	No
`cursor`	No	Archive continuation token; reuse with snapshot ID/hash, as_of and unchanged filters.
`family`	No
`offset`	No
`ticker`	Yes
`context`	Yes	User's research goal in one short sentence (max 300 characters); include relevant ticker and topic. Exclude names, contact/account/portfolio details, credentials and source text.
`date_to`	No	Inclusive native date upper bound, selected by date_field.
`date_from`	No	Inclusive native date lower bound, selected by date_field.
`llm_model`	Yes	Your model identifier, if known (e.g. gpt-6); otherwise leave unknown. Exclude credentials and private deployment names.
`date_field`	No	Date meaning; defaults to period for facts/macro/holdings/returns, event for insider trades, observation for options/short volume, scheduled for calendar.
`strike_max`	No
`strike_min`	No
`snapshot_id`	No	Pin continuation to the returned snapshot ID; reuse with snapshot_hash and as_of.
`activity_type`	No
`expiration_to`	No
`snapshot_hash`	No
`filters_sha256`	No	Reuse the returned filter hash unchanged with continuation pages.
`conversation_id`	No	Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request.
`expiration_from`	No
`max_snapshot_age_hours`	No	Requested verification-age tolerance: default1hour for retained archives,24hours for closing-price references. Record dates and publication cadence are separate.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 9, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Adds substantial behavior beyond the annotations: metered cost ('Uses account allowance or prepaid credit'), freshness semantics where current requests recheck stale mirror metadata while historical/pinned reads stay fixed, non-sorted source ordering, and the rule that partial scans are not proof of no matches. This also helps explain why readOnlyHint is false for a retrieval tool. No contradiction, though the return-shape sentence largely duplicates what the output schema already conveys.

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

Conciseness4/5

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

Purpose and scope are front-loaded, and every sentence carries operational content with no filler. Some clauses are compressed to the point of opacity, e.g. 'Current requests recheck stale mirror metadata; historical/pinned reads remain fixed,' which costs a little readability without wasting words.

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 22-parameter tool with an output schema, the description covers cost, caching/availability semantics, filter strategy, continuation via cursor/next_offset, and the incompleteness caveat. The main remaining gap is how to resolve overlapping selectors (family vs activity_type) and what happens when no activity_type is supplied.

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 coverage is only 55% across 22 parameters, so the description must compensate; it names activity_type, right, expiration, strike and observation-date filters, and distinguishes open interest as a position measure from volume as a flow. However, it leaves enum parameters such as family (options vs open_interest) and the relationship between family and activity_type unexplained, and says nothing about offset, snapshot_hash, or the strike_min/strike_max bounds.

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?

Opens with a specific verb and resource pair: 'Retrieves retained options bars, flow aggregates and open interest for one ticker.' It enumerates the three activity types and the filterable dimensions, which lets an agent separate it from siblings like get_short_activity or get_market_returns without opening the schema.

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?

Gives practical selection guidance: choose activity_type and the call/put, expiration, strike and observation-date filters, and 'Use explicit date/instrument filters for large histories.' It also warns that 'source-file order is not a globally sorted latest option chain' and that partial scans are inconclusive. It stops short of naming a sibling as an alternative or stating when not to use this tool.

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

All BeliefState tools Inspect

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.