Bullrun

Screen ETFs

screen_etfs

Read-only

Screen the WHOLE ETF universe by numeric rules and fund attributes in one pass — expense ratio, AUM, yield, trailing returns, volatility, liquidity, top-10 concentration, fund age and holdings count — combined with issuer, index, domicile, UCITS status, distribution policy, currency hedging and constituent look-through (holdingSearch finds funds by what they hold). Prefer this over search_etfs for any "cheapest / largest / best performing / most liquid" question: search_etfs only filters a bounded candidate scan, while this evaluates the full universe and reports evaluatedCount and matchCount. Percentages are percentage points. This is the heaviest read in the API and is metered against a small per-day action budget, so build one well-specified screen rather than probing repeatedly. Read-only.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`limit`	No	Maximum ETFs to return, 1-100.
`order`	No	Sort direction. Nulls always sort last regardless of direction.	desc
`rules`	No	Numeric rules. A fund with no value for a ruled metric never matches that rule.
`issuer`	No	Substring match on the fund family/issuer, e.g. "iShares", "Amundi", "Vanguard".
`region`	No	Exact investment-region string.
`search`	No	Free-text match on ticker, fund name or ISIN. Omit to screen the whole universe.
`sortBy`	No	Sort field applied to the returned rows.	totalAssets
`category`	No	Exact category string. Call get_etf_filter_options for the valid values; a wrong guess silently returns zero rows.
`currency`	No	Exact trading currency, e.g. EUR, USD, GBX.
`domicile`	No	Exact fund domicile, e.g. "Ireland", "Luxembourg", "United States".
`exchange`	No	Exact listing exchange, e.g. XETRA, LSE, "NYSE ARCA".
`indexKey`	No	Exact tracked-index key, e.g. SP500, MSCI_WORLD, NASDAQ100. Use get_etf_index_group to compare every fund on one index instead.
`strategy`	No	Exact strategy classification string.
`assetClass`	No	Exact asset-class group: EQUITY, FIXED_INCOME, COMMODITY, REAL_ESTATE, MULTI_ASSET, CASH, CURRENCY, DIGITAL_ASSETS, ALTERNATIVES or OTHER.
`holdingMode`	No	INCLUDES keeps funds holding the constituent. EXCLUDES keeps only funds with a holdings snapshot that confirms absence — funds with no snapshot are dropped, never assumed clean.	INCLUDES
`productType`	No	Exact wrapper type, e.g. UCITS_FUND.
`ucitsStatus`	No	UCITS restricts to wrappers a European retail investor can actually buy.
`holdingSearch`	No	Look-through filter: find funds by a CONSTITUENT ticker or company name, e.g. "NVDA" or "NVIDIA". Only funds with a stored holdings snapshot can match.
`currencyHedged`	No	HEDGED selects funds labelled currency-hedged. NOT_LABELLED_HEDGED selects funds not so labelled — absence of a label is not proof a fund is unhedged.
`benchmarkSearch`	No	Substring match on the stated benchmark name.
`includeSecondary`	No	Include secondary venue listings of the same fund. Default false — one row per fund's primary listing.
`marketDevelopment`	No	Exact market-development classification, e.g. developed vs emerging.
`distributionPolicy`	No	Accumulating (reinvests income) or distributing (pays it out) — the usual first cut for a European investor.
`holdingMinWeightPct`	No	Minimum constituent weight in percentage points for holdingSearch to count as a match.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`query`	Yes
`results`	Yes
`coverage`	Yes
`returned`	Yes
`warnings`	Yes
`matchCount`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

AddedAug 17, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Beyond the readOnlyHint annotation, the description discloses important behavioral and operational details: this is 'the heaviest read in the API', metered against a small per-day action budget, and that 'Percentages are percentage points' — clarifying output semantics. This adds real context beyond what annotations alone provide.

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?

Despite describing a 24-parameter tool, the description is compact and front-loaded. Three sentences cover purpose, usage guidance, behavioral caveats, and unit semantics with zero filler or redundancy. Every sentence earns its place.

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 output schema exists, and the description covers the full screening scope, the differentiation from a sibling tool, rate limiting, and result reporting (evaluatedCount, matchCount). Nothing crucial is missing for an agent to select and invoke this tool effectively.

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

Parameters4/5

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

The schema already covers 100% of parameters, so the baseline is 3. The description adds value by grouping parameters into mental categories (expense ratio, AUM, yield, etc.) and by clarifying that holdingSearch 'finds funds by what they hold', plus the percentage-points note. This helps an agent quickly understand relationships between the many metrics.

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 'Screen the WHOLE ETF universe by numeric rules and fund attributes in one pass', which is a specific verb (screen) plus a clearly defined resource (whole ETF universe). It immediately distinguishes itself from search_etfs by contrasting full-universe evaluation versus a bounded candidate scan.

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?

Explicit usage guidance is provided: 'Prefer this over search_etfs for any cheapest / largest / best performing / most liquid question' and it names the alternative tool. It also warns against probing repeatedly due to a per-day action budget, giving the agent clear when-to-use and when-to-avoid guidance.

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

All Bullrun 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.