Bullrun

Search ETFs

search_etfs

Read-only

Look up ETFs by name, ticker or ISIN, with classification, listing, index, distribution-policy, AUM, expense-ratio and yield filters. Best for finding a known fund. For ranking questions ("cheapest", "largest", "best performing", "most liquid") prefer screen_etfs, which evaluates the whole universe: here minAum and minYieldTtmPct are applied only to a bounded profile-enriched candidate scan, so do not describe the result as exhaustive when candidateCapReached is true. Use get_etf_snapshot for one listing, get_etf_fund to resolve an ISIN across venues, and get_etf_holdings for constituents. Read-only.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`focus`	No	Exact ETF focus/exposure filter, e.g. Japan, TOPIX, or Equity - Australia.
`limit`	No	Maximum matching ETFs to return, 1-100.
`minAum`	No	Minimum assets under management in the profile's reported currency units.
`region`	No	Exact portfolio or investment-region filter.
`search`	No	Free-text ETF search by ticker, fund name, or ISIN (e.g. IE00B4L5Y983). Omit for a broad screen.
`sortBy`	No	Sort field. Relevance preserves Bullrun search ordering.	relevance
`category`	No	Exact broad ETF category/asset-class filter, e.g. Equity, Fixed Income, Commodity, Crypto, or Real Estate. Call get_etf_filter_options for valid values.
`currency`	No	Exact trading-currency filter.
`domicile`	No	Exact fund domicile filter.
`exchange`	No	Exact listing exchange filter.
`indexKey`	No	Exact tracked-index key, e.g. SP500 or MSCI_WORLD. Use get_etf_index_group to rank every fund on one index by cost.
`scanLimit`	No	Maximum coarse-search candidates to enrich before applying quantitative filters/sorts, 25-500.
`sortDirection`	No		desc
`minYieldTtmPct`	No	Minimum trailing yield in percentage points, e.g. 2 means 2%.
`includeInactive`	No
`includeSecondary`	No
`distributionPolicy`	No	Accumulating (reinvests income) or distributing (pays it out).
`maxExpenseRatioPct`	No	Maximum annual expense ratio in percentage points, e.g. 0.25 means 0.25%.

Output Schema

TableJSON Schema

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

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedAug 17, 2026

changedInput schema / properties / category / description

Previous value: -"Exact broad ETF category/asset-class filter, e.g. Equity, Fixed Income, Commodity, Crypto, or Real Estate."New value: +"Exact broad ETF category/asset-class filter, e.g. Equity, Fixed Income, Commodity, Crypto, or Real Estate. Call get_etf_filter_options for valid values."

addedInput schema / properties / distributionPolicy

Added value: +{
+  "description": "Accumulating (reinvests income) or distributing (pays it out).",
+  "enum": [
+    "ACCUMULATING",
+    "DISTRIBUTING"
+  ],
+  "type": "string"
+}

addedInput schema / properties / indexKey

Added value: +{
+  "description": "Exact tracked-index key, e.g. SP500 or MSCI_WORLD. Use get_etf_index_group to rank every fund on one index by cost.",
+  "type": "string"
+}

changedInput schema / properties / search / description

Previous value: -"Free-text ETF search by ticker or fund name. Omit for a broad screen."New value: +"Free-text ETF search by ticker, fund name, or ISIN (e.g. IE00B4L5Y983). Omit for a broad screen."

AddedAug 11, 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 a critical behavioral trait: minAum and minYieldTtmPct are applied only to a 'bounded profile-enriched candidate scan', and warns not to describe results as exhaustive when candidateCapReached is true. This prevents misinterpretation of results and goes above and beyond what annotations provide. No contradiction with annotations.

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 three sentences, information-dense, and front-loaded with purpose. Every sentence earns its place: purpose/filters, usage guidance with alternatives, and the critical non-exhaustiveness caveat. No wordiness or repetition.

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 an 18-parameter tool with a rich schema and output schema, the description covers the primary use case, differentiates from relevant siblings, explains the main limitation, and directs users to specialized tools. It is complete enough without needing to restate schema content.

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?

Schema description coverage is high (83%), so a baseline of 3 applies. The description adds meaningful parameter context by explaining that minAum and minYieldTtmPct operate on a bounded candidate scan, clarifying their effect. It also maps the search parameter to 'name, ticker or ISIN' and lists filter categories that map to several parameters. This adds value beyond the schema without covering every parameter.

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 uses a specific verb ('Look up') and identifies the resource (ETFs) plus scope (by name, ticker or ISIN) and filter domains (classification, listing, index, etc.). It explicitly distinguishes from screen_etfs by stating it is 'Best for finding a known fund', and names other sibling tools for different use cases, providing clear differentiation.

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 explicit when-to-use guidance ('Best for finding a known fund'), when-not-to-use ('For ranking questions... prefer screen_etfs'), and prescribes alternative tools ('Use get_etf_snapshot for one listing, get_etf_fund to resolve an ISIN across venues, and get_etf_holdings for constituents'). This is exemplary usage direction.

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.