Skip to main content
Glama

Screen funds

screen_funds
Read-onlyIdempotent

Screen funds and ETFs: the funds that pass a screen, one line each, unweighted and unsaved.

One named fund is found with find_assets; stocks with screen_equities. The listed
asset_ids are the items solve_allocation_weights and build_allocation_strategy take.

Where a card is drawn, the client can also add any fund to its shortlist by name or
ISIN, open a fund's details and set another fund beside it there. To compare funds
the client names, open them with open_dashboard instead.

Labels classify each fund's mandate; a label a fund type lacks screens that type
out. A platform in ``fund_lists`` also passes EEA-domiciled ETFs where it is a
broker; an own list alone lists its funds with their figures. The result names the
fund lists this client can use. Fees are the ongoing charge (OCF/TER), percent a
year. Each fund's risk level places its volatility on the platform's 0-10 scale.
Volatility and returns are percent in the client's currency; 3y and 5y returns are
annualised
and need that much price history. An unknown figure fails a limit set on it. A
fund's share classes fold into one line: the class in the client's currency, else
the cheapest. The 0-10 rating ranks a fund within its peer group on five-year
risk-adjusted return after fees; it does not compare segments.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "screen_funds"
  }
}

Input Schema

NameRequiredDescriptionDefault
coinsNo
sizesNo
searchNoName, manager or ISIN text to match.
stylesNo
themesNo
excludeNoNames or managers whose funds are dropped.
regionsNoThe fund's own mandate: region groups, or ISO-3 codes for single-country funds. A Nordic fund is not a Sweden fund.
sectorsNo
sort_byNoongoing_charge
vehiclesNo
durationsNo
bond_typesNo
fund_listsNoFund lists a fund must be on: a platform code in the client's market (where they buy) or the name of one of the client's own lists. Funds on any platform named pass, and on any own list named; naming both kinds keeps the funds that pass each.
managementNo'active' is every fund not known to track an index.
min_ratingNoFunds rated at least this, 0-10.
min_returnNoPercent a year over return_years, in the client currency.
distributionNoKnown for few funds yet; a fund whose policy is unknown fails it.
return_yearsNo
asset_classesNo
max_risk_levelNoThe highest risk level to keep, on the 0-10 scale (0 cash, 2 longer bonds, 5 half shares and half bonds, 8 global shares, 10 a single sector).
commodity_groupsNo
include_leveragedNo
min_history_yearsNo
max_ongoing_chargeNoPercent a year.
maximum_number_of_fundsNoFunds listed, in the text as on the card: at most 500; default 100.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior5/5

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

Goes well beyond the readOnly/idempotent annotations: results are unweighted and unsaved, an unknown figure fails any limit set on it, share classes fold into one line (client-currency class, else cheapest), 3y/5y returns require that much price history, and the 0-10 rating is a within-peer-group five-year risk-adjusted-after-fee rank. These are exactly the behaviors an agent cannot infer from annotations or schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

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

Purpose and alternatives are front-loaded, but the body is a dense wall of sentences mixing screening semantics with client-UI behavior (shortlisting by name or ISIN, opening details, setting a fund beside another), which is tangential to invoking this tool. Several clauses ('a label a fund type lacks screens that type out') are terse to the point of being hard to parse.

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

Completeness4/5

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

For a 25-parameter screener with no output schema, the description covers the important unknowns: line-per-fund output, unsaved/unweighted results, fund-list echo in the result, and fee/risk/return units and currency. Remaining gaps are the undocumented enum filters rather than missing output or behavioral context.

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?

With 25 parameters at 44% schema coverage the description must compensate, and it does for the trickiest ones: fund_lists union semantics across platform codes and own lists, management meaning 'not known to track an index', distribution failing unknown policies, max_risk_level with an anchor scale, min_return currency basis, and maximum_number_of_funds default of 100. It still leaves many enums (coins, sizes, styles, sectors, durations, commodity_groups, include_leveraged, min_history_years) to the schema alone.

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?

States a specific verb and resource ('Screen funds and ETFs') plus the exact output shape ('the funds that pass a screen, one line each, unweighted and unsaved'). It immediately differentiates from siblings by naming find_assets for a single named fund and screen_equities for stocks.

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?

Explicitly routes the agent: single fund lookups go to find_assets, stocks to screen_equities, and comparing client-named funds to open_dashboard. It also states downstream usage by naming solve_allocation_weights and build_allocation_strategy as the consumers of the returned asset_ids.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources