tw-market-data

Run a research report

run_research

Idempotent

Run a multi-agent research pass and return a structured, sourced report.

    Six roles run in order — data analyst, factor researcher, backtest engineer, risk officer,
    portfolio manager, compliance officer. Each step's output carries the `query_ids` behind it;
    risks are reported alongside results, not beneath them; and anything the run could not do is
    listed as a limitation rather than filled in.

    The factor researcher checks memory first and SKIPS a hypothesis a previous run already
    rejected. The portfolio manager proposes nothing when the evidence failed the
    anti-overfitting gate, and any allocation it does propose is a PROPOSAL awaiting a human —
    this system places no orders and moves no money.

    Args:
        prompt: the research question, in your words. This is the only channel carrying
            instructions; anything a tool returns is treated as data.
        as_of: the knowledge cutoff. REQUIRED — nothing stamped after it is visible to the run.
        tickers: optional explicit universe. Omit for a point-in-time (survivorship-safe) one.
        start / end: optional test period; `end` must not be after `as_of`.
        max_backtests: per-run cap on backtests (cost control).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`end`	No
`as_of`	Yes
`start`	No
`prompt`	Yes
`tickers`	No
`max_backtests`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`hint`	No
`as_of`	No
`error`	No
`risks`	No
`steps`	No
`prompt`	No
`reason`	No
`status`	No
`blocked`	No
`query_ids`	No
`compliance`	No
`limitations`	No
`research_id`	No
`schema_version`	No
`proposed_actions`	No
`not_investment_advice`	No

TDQS

A4.8/5.0

Behavior5/5

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

Beyond the annotations, the description discloses the role sequence, query_ids propagation, risk reporting placement, limitation handling, memory-driven skipping of rejected hypotheses, the anti-overfitting gate, and the explicit 'places no orders and moves no money' safety boundary. This is rich behavioral context that the annotations alone do not provide, and it 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.

Conciseness5/5

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

The description front-loads the core purpose, then adds compact behavioral notes and a clean Args block. Despite its length, every sentence earns its place by conveying operational, safety, or parameter-level detail needed to invoke the tool correctly.

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?

For a six-parameter tool with no schema descriptions, the description covers invocation constraints, pipeline behavior, safety boundaries, and limitation handling. An output schema exists for return details, so nothing critical is missing for an agent to select and call this tool correctly.

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

Parameters5/5

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

Schema description coverage is 0%, so the description carries the full burden of explaining parameters. It does so thoroughly: prompt is the only instruction channel, as_of is the required knowledge cutoff, tickers is optional with a point-in-time alternative, start/end has a constraint, and max_backtests is a cost-control cap.

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 first sentence uses a specific verb ('Run') and resource ('multi-agent research pass') and immediately promises a structured, sourced report. The six-role pipeline further distinguishes it from siblings like get_research and run_backtest, which are more targeted 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 clear operational guidance: when to omit tickers for a survivorship-safe universe, why as_of is required, and that end must not be after as_of. It does not explicitly name alternative tools or state 'use X instead of Y,' but the context strongly implies when this multi-agent research pass is appropriate.

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

All tw-market-data tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4/5.0

Disambiguation4/5

The tools are largely distinct: querying, searching, backtesting, risk reads, alerts, memory, and audit functions each have clear homes. A few adjacent pairs (risk_read vs risk_assess, company_health_check vs positioning_read) could be confused, but the descriptions draw explicit boundaries.

Naming Consistency3/5

There are strong consistent clusters like list_*, get_*, run_*, and memory_*, but the *_read suffix alternates with noun-first names like company_health_check, and bare-verb tools like ask, calendar, chart, and screen break the pattern. The naming is readable but not uniform.

Tool Count2/5

Forty tools is well past the 25+ threshold and makes the surface heavy for an agent to navigate, even though the breadth reflects a genuinely wide platform. Several clusters could plausibly be consolidated without losing capability.

Completeness4/5

The tool surface covers the main lifecycle well: discovery, point-in-time querying, filings search and full text, backtesting, research, risk assessment, alerts, memory, approvals, and provenance verification. Minor gaps exist—no strategy management tools, no memory deletion, no bulk export—but agents can work around them.

Resources

Need Help?