tw-market-data

Explain where a value came from

explain_provenance

Read-onlyIdempotent

Where did this number come from, and when could anyone have known it? (WP-6)

★ THIS IS THE GROUNDING TOOL. Every other tool's answer is supposed to be expandable through
this one: given a ticker, a field and a date, it names the dataset that serves that field, the
knowledge column, and WHICH as_of rule applies on that date. Use it whenever you are about to
state a number as fact.

★ IT DOES NOT OVERLAP WITH THE OTHER TWO PROVENANCE TOOLS, and they are not substitutes:
  `get_inclusion_proof(dataset, row_key)`  proves a ROW was in a published snapshot (Merkle).
  `cite_this(dataset, as_of)`              produces a citation for a DATASET.
  `explain_provenance(ticker, field, date)` answers WHERE A CELL came from and WHEN it was
                                            knowable. Nothing else answered that.

★ FOUR VERDICTS, and `partial` is not `resolved`:
  resolved         dataset, knowledge axis, as_of rule AND the official endpoint.
  partial          ⚠️ the first three, but NOT the official endpoint — no dataset declares a
                   per-cell endpoint today. "When was it knowable" and "which official
                   endpoint produced it" are different questions; conflating them is exactly
                   the vagueness this tool exists to remove.
  ambiguous_field  ⚠️ the field lives in several datasets. Every candidate is listed and NONE
                   is picked for you: picking one would hand you a confident wrong answer.
                   Re-ask with `dataset=`.
  unknown_field    no served dataset declares that field. This is "we do not have that
                   column", NOT "no data found" — a different next step for you.

★ READ `limitations`. It says when the knowability date is DERIVED (statutory deadline, a
conservative upper bound) rather than observed, and whether the rule came from declarations or
from the live schema. A declared capability is not the same as a working one.

Args:
    ticker: the security, e.g. '2330'.
    field: the column you are about to quote, e.g. 'close', 'revenue'.
    date: the date your claim is about (YYYY-MM-DD).
    dataset: pin the answer to one dataset when the field is ambiguous.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`date`	Yes
`field`	Yes
`ticker`	Yes
`dataset`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

TDQS

A5/5.0

Behavior5/5

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

Although annotations already mark the tool as readOnly, idempotent, and open-world, the description adds substantial behavioral detail beyond them: the four possible verdicts, the critical warning that 'partial' is not 'resolved', the fact that ambiguous_field deliberately lists candidates without picking one, and that unknown_field means 'we do not have that column' rather than 'no data found'. It also directs the agent to read limitations for derived-versus-observed knowability dates. No contradiction with annotations exists.

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 long, but every section earns its place: the purpose, the sibling non-overlap, the verdict semantics, the limitations warning, and the parameter examples. It is front-loaded with the most important usage guidance and uses formatting (stars, verdict names, bolded warnings) to make the dense content scannable. None of the text is redundant with the schema or annotations.

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?

Given the tool's complexity, the description is remarkably complete. It covers when to use the tool, what each verdict means, how to handle ambiguous fields, what limitations to consult, and what each parameter represents. The presence of an output schema relieves it of explaining return-value structure, and the description instead addresses the conceptual traps that would otherwise lead an agent astray.

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?

With 0% schema description coverage, the description carries the full burden of explaining parameters, and it does so well. Each parameter gets a concrete definition and example: ticker as '2330', field as 'close' or 'revenue', date as YYYY-MM-DD, and dataset as a disambiguation pin. The dataset parameter's role in the ambiguous_field case is also explained, which is exactly the semantic insight an agent needs beyond the raw 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 the exact question the tool answers — 'Where did this number come from, and when could anyone have known it?' — then states the precise operation: given a ticker, field, and date, it names the dataset, knowledge column, and applicable as_of rule. It also distinguishes itself from the sibling provenance tools by explicitly stating what it is not, so an agent can confidently tell it apart from get_inclusion_proof and cite_this.

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

Usage Guidelines5/5

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

The description gives an explicit trigger condition: 'Use it whenever you are about to state a number as fact.' It also names the two sibling provenance tools and explains why they are not substitutes, each with its own one-line purpose. It even prescribes the next step for ambiguous_field results — re-ask with dataset= — so the agent knows exactly when and how to adjust its invocation.

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?