Skip to main content
Glama

Kaleidoscope MCP (SEC & financial data)

Adviser RAUM Decliners (forced-seller / Redemption Watchlist — discretionary-RAUM drops + basis-change guard)

adv_raum_decliners
Read-onlyIdempotent

Forced-seller / Redemption Watchlist tool. Returns advisers whose discretionary RAUM fell between their two most recent ADV filings, ranked by percent decline. Pair with thirteenf_portfolio_full(cik=...) to surface specific equities under redemption-driven selling pressure ('which stocks face forced selling this quarter').

Backed by a pre-computed table (proc2.adv.firm_raum_decliners, 3,423 rows / 816 with cik). Daily blue/green refresh. Sub-2ms warm.

Two correctness-critical design choices baked in upstream by adv — surface these in any prompt that consumes the output:

  1. Decline is computed on DISCRETIONARY RAUM, not total. The Sageview case is the canonical false-positive class: −84% on total RAUM ($238.6B → $37.5B) but +0.5% on discretionary — the entire $201B drop was a nondiscretionary reclassification, NOT a redemption. Sageview never enters the table because the filter is discretionary-only. Don't second-guess the table by re-computing off total.

  2. basis_change_suspect=true flags the residual cases where discretionary DID fall but the discretionary/total mix also shifted >20pts. These are likely reporting-basis reclassifications, NOT redemptions (K1 Investment Mgmt, GraniteShares ETF reclass are typical examples). The tool default excludes these (include_basis_changes=false). Set include_basis_changes=true only if you're auditing the data; never include them in 'who's facing forced selling' answers.

Killer acceptance case (per spec): Politan Capital Management (crd 316047, cik 1885245) → drop_pct=46.04, basis_change_suspect=false. The Masimo (MASI) campaign — clean redemption signal. Chain into thirteenf_portfolio_full(cik=1885245) for the at-risk equity book.

No as_of param — by design (adv team's position 2026-06-12, futures agreed): the table always compares each adviser's two MOST RECENT filings to detect discretionary-RAUM declines. Adding as_of would conflict with that purpose. For replay backtests at a past date, reconstruct equivalent decline signals from adv_manager_raum_trend(crd, limit=8) — the trend tool's rows carry their own as_of (Pattern B PIT, ~300K rows across all filings), so a client-side cutoff to as_of + take the two most recent ≤ as_of + compute (1 - latest_disc/prior_disc) reproduces the decliner detection PIT-correctly.

Filters (all index/scan-fast):

  • min_drop_pct (default 30) — minimum % discretionary decline

  • min_prior_raum_disc (default 1e9) — prior-filing discretionary RAUM in USD; use to anchor on size (1e9 = $1B+ advisers, which is the futures team's default for the Redemption Watchlist)

  • min_latest_asof — only include advisers whose latest filing is on/after this date (YYYY-MM-DD); use to scope to a recent vintage

  • with_cik_only (default true) — restrict to advisers with a resolved SEC CIK (the 13F-joinable subset; the whole point is chaining into thirteenf_*). Coverage gap: only a minority of >$1B-prior-disc decliners resolve to a cik today — adv's CRD↔CIK bridge backfill is in flight; universe widens over time.

  • include_basis_changes (default false) — set true to opt back in (audit only)

  • sort ∈ {drop_pct_desc (default), prior_raum_disc_desc, latest_asof_desc}

  • limit (default 50, max 200)

Spec-validated counts (for sanity): no filters → 3,423; with_cik_only=true → 816; min_drop_pct=30 + min_prior_raum_disc=1e9 + with_cik_only=true + NOT basis_change_suspect (the worked default) → 60 advisers.

Each row carries prior_source_filing_id / latest_source_filing_id (the two Form ADV filings the prior / latest RAUM come from).

Every adviser crd in the output has the adviser's SEC cik beside it (#2287; x_crd -> x_cik, a CRD list -> ..._crd_ciks): the CIK of the 13F filer that reports under that CRD, else the CIK on its own Form ADV; ciks lists both when they differ; null when neither exists. A row that already had its own cik keeps it.

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": "adv_raum_decliners"
  }
}

Input Schema

NameRequiredDescriptionDefault
sortNoSort order. drop_pct_desc (default) = biggest decline first.drop_pct_desc
limitNoMax rows (default 50, max 200).
min_drop_pctNoMinimum discretionary-RAUM % decline (0-100). Default 30 (the futures team's Redemption Watchlist baseline).
with_cik_onlyNoIf true (default), restrict to advisers with resolved SEC CIK (the 13F-joinable subset). Set false only when you want the full discretionary-decliner universe regardless of 13F-chainability.
min_latest_asofNoOnly include advisers with `latest_asof >= this YYYY-MM-DD`. Use to scope to recent vintages.
min_prior_raum_discNoMinimum PRIOR-filing discretionary RAUM in USD. Default 1e9 ($1B+) — typical forced-seller universe.
include_basis_changesNoDefault false — exclude rows where `basis_change_suspect=true` OR NULL (basis-change-unknown). Set true ONLY when auditing data quality; NEVER include these in 'who's facing forced selling' answers — they're reporting-basis reclassifications, not redemptions.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description layers on substantial context beyond them: pre-computed table identity, row counts, daily blue/green refresh, sub-2ms latency, and a documented coverage gap (only a minority of >$1B decliners resolve to a CIK). It also discloses the discretionary-only methodology and the basis_change_suspect exclusion that shapes the result set, which an agent cannot infer from annotations.

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 is front-loaded and the bold/labeled structure is easy to scan, but the piece runs long for a 7-param read tool. The 'killer acceptance case' narrative, the spec-validated count breakdown, and the 'adv team's position 2026-06-12' provenance are closer to internal test documentation than invocation guidance, and several filter descriptions are duplicated in both prose and schema.

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 a filtered list tool with no output schema, the definition covers expected row contents (source filing ids, crd/cik/ciks resolution rules), sanity-check counts for the worked default, and the chaining path into thirteenf_portfolio_full. Nothing an agent needs to call it correctly or interpret the output is missing.

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?

Schema coverage is 100%, yet the description still adds meaning: min_prior_raum_disc anchored to the futures team's $1B default, with_cik_only framed as the 13F-chainable subset with known undercounting, include_basis_changes tied to a concrete false-positive class (K1, GraniteShares), and the reasoned absence of as_of. This goes well past restating schema text.

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?

Opens with a specific verb and resource: 'Returns advisers whose discretionary RAUM fell between their two most recent ADV filings, ranked by percent decline.' It also labels the domain use case (forced-seller/Redemption Watchlist) and explicitly points to adv_manager_raum_trend for the PIT-replay variant, so an agent can distinguish it from siblings without opening a schema.

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?

Gives explicit when-to-use (chain into thirteenf_portfolio_full to find at-risk equities), when-not-to (never include basis-change suspects in 'who's facing forced selling' answers), and a named alternative for backtests (reconstruct from adv_manager_raum_trend with client-side as_of cutoff). It even states why no as_of param exists, closing the obvious 'can I scope by date' question.

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