ta-catalyst

Historical move analysis

history_move_analysis

Read-onlyIdempotent

Analyze why a stock moved over a past window by cross-checking independent technical, company-news, and macro reads, then classify each move as explained, unexplained, overreaction, or underreaction.

Instructions

Explain what moved a stock over a past window, and why.

Runs three INDEPENDENT reads that are blind to each other, then reconciles them:

A technical read of price and volume, with NO news context. Its value is that it is independent -- told the news first, a model narrates the chart to fit the story.
A search of company-specific catalysts (earnings, guidance, ratings, legal, product).
A deterministic read of the macro complex, then a search of macro news driven by what actually moved.

A deterministic scan first picks the significant trading days, so all three work from the same calendar. Each such day is then classified:

explained move with a matching catalyst unexplained a real move, news WAS searched, nothing found -- implies flow, positioning or genuine technical behaviour, and the technical read deserves MORE weight here overreaction move much larger than the catalyst warrants underreaction catalyst much larger than the move -- priced in no_ta / no_catalyst_coverage that stream was not run; NOT a finding about the market

Read coverage before the verdicts. A false there means the stream was never run, and absence of a search is not absence of a catalyst.

Turning every branch off returns coverage only, with no verdicts.

Input Schema

TableJSON Schema

Name	Required	Description
`as_of`	No	Point-in-time cutoff, ISO YYYY-MM-DD. Every data source hard-truncates here, so a backtest cannot see the future. Omit for live data.
`months`	No	Lookback in months. Ignored when start_date and end_date are both given.
`ticker`	Yes	Ticker symbol, e.g. 'NVDA'. Case-insensitive.
`end_date`	No	Window end, ISO YYYY-MM-DD.
`session_id`	No	Reuse a previous call's session to ask a follow-up without recomputing. Omit for an independent run.
`start_date`	No	Window start, ISO YYYY-MM-DD.
`include_macro`	No	Read the macro complex (QQQ, SPY, dollar index, 10-year yield, gold, VIX) and search macro news.
`include_technical`	No	Run the blind technical read of the chart.
`include_company_news`	No	Search company-specific catalysts.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 21, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Beyond the readOnly/idempotent annotations, the description reveals substantial behavioral detail: the three reads are intentionally blind to each other, significant days are picked deterministically before any analysis, and each classification (explained, unexplained, overreaction, underreaction, no_ta/no_catalyst_coverage) carries a distinct meaning. This exceeds what annotations alone convey and contradicts nothing.

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?

The description is well-structured: purpose is front-loaded, and the numbered reads plus bullet-like classification list make complex behavior scannable. It is long, but the length is mostly earned by the tool's inherent complexity; slight redundancy around the technical read's independence keeps it from being maximally tight.

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

Completeness5/5

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

With an output schema present, the description correctly focuses on interpretation rather than return shape. It explains the significance of coverage false values, warns that absence of a search is not absence of a catalyst, and clarifies how deterministic day selection binds the three streams together. Nothing needed to invoke or interpret the tool correctly is missing.

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 100%, so the schema already documents every parameter well and the description does not need to repeat them. The description does add contextual meaning for branch flags, such as the technical read running with no news context and all branches off returning coverage only, but it does not add per-parameter syntax or format details beyond the schema.

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 opens with a specific verb and resource: 'Explain what moved a stock over a past window, and why.' It then details the exact method (three independent reads reconciled into verdict categories), so an agent knows precisely what the tool does and how it differs from a generic historical quote or news tool.

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?

There are no sibling tools to distinguish against, but the description gives clear operational guidance: which branches can be toggled, what happens when branches are disabled, and how to interpret coverage before verdicts. It does not explicitly state 'use when X instead of Y' because no alternatives exist, so it stops just short of a 5.

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

Deploy Server

Other Tools

history_move_analysisA