Skip to main content
Glama

Index Fund Flows and Rebalance Trades

GetIndexFundFlows
Read-only

Get the money flowing into or out of the fund that tracks an index, and what that fund bought and sold for the index at its last rebalance. Covers the indexes whose tracking fund publishes a daily holdings file, such as the S&P 500 (IVV), S&P MidCap 400 (IJH), S&P SmallCap 600 (IJR), Russell 1000 (IWB) and Russell 2000 (IWM). A flow is an estimate: creating or redeeming units scales every holding alike, so the median change in the fund's share counts between two daily files is its flow, applied to the fund's value. It is that one fund's money, not demand for the index. A rebalance is the newest session where at least one holding in ten moved more than 2% apart from the fund's flow; those holdings were traded for the index itself. The trade lists rank every holding more than 0.1% apart from the flow by dollar value, so a small adjustment to a large company can lead them. Use GetIndexChanges for the companies that joined or left.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "index": "<index>"
    },
    "name": "GetIndexFundFlows"
  }
}

Input Schema

NameRequiredDescriptionDefault
indexYesIndex name or slug, for example "S&P 500", "sp-500", "S&P MidCap 400" or "Russell 2000".

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered by structured data. The description's real contribution is interpretive: the flow is 'an estimate', is derived from median share-count changes across daily files, 'is that one fund's money, not demand for the index', and rebalances are detected via a 2% threshold with trades ranked by 0.1% deviation — useful caveats that go beyond the annotations. It stops short of stating the response shape or whether a fixed lookback window applies, so against low-burden annotations this is a solid mid-tier rather than rich behavioral disclosure.

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

Conciseness4/5

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

The first sentence front-loads the purpose, and the exclusions land last, which is the right ordering. The middle methodology sentences are dense and occasionally roundabout ('the median change in the fund's share counts between two daily files is its flow, applied to the fund's value'), packing definitional detail that is useful for interpretation but could be tightened without losing meaning.

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?

With no output schema, the description carries the burden of explaining what comes back, and it does: a flow estimate for the fund, a detected rebalance session, and trade lists ranked by dollar value with the caveat that 'a small adjustment to a large company can lead them.' What remains unstated is the temporal scope of the flow estimate and whether results are per-fund or per-index only — small gaps for a single-parameter read tool.

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

Parameters3/5

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

There is a single required parameter and schema description coverage is 100%, so the schema already documents that `index` accepts a name or slug. The description's index list (S&P 500, MidCap 400, SmallCap 600, Russell 1000/2000) reinforces valid values but adds no format or disambiguation rules beyond what the schema states. Baseline 3 is appropriate when the schema does the work.

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 names a specific resource and two distinct outputs — 'money flowing into or out of the fund that tracks an index' and 'what that fund bought and sold for the index at its last rebalance' — then anchors them with concrete index examples (IVV, IJH, IJR, IWB, IWM). It explicitly carves out the boundary with 'Use GetIndexChanges for the companies that joined or left,' so an agent can distinguish it from the nearest sibling without opening any schema.

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?

It gives a clear applicability condition — 'Covers the indexes whose tracking fund publishes a daily holdings file' — plus a named alternative with the condition that selects it (GetIndexChanges for additions/removals). It does not state what to do when the requested index has no tracking fund or no daily file, which keeps it below a 5.

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.