asset-management

Overview Schema Source Related Servers Discussions Admin

discover_gaps

Read-onlyIdempotent

Pinpoint underweight roles in the portfolio (≤3% market value) and find comparable funds from standard shelves to fill each gap. Avoids flagging sector-equity as a hole.

Instructions

Roles the user's portfolio is light in (≤3% of market value), each with comparable funds from its standard SHELF — core funds first, so a style tilt or junk bond never fills a gap while a plain option exists (offline, read-only, propose-only). other_shelves names the role's other sub-exposures (treasury durations, REIT geography) without picking one: choosing a shelf is the user's decision. The sector-equity satellite is never flagged as a gap (a tactical bet, not a hole) — call with role='sector-equity' to get its shelf map, then add flavor= to see one shelf's funds. A gap means no dedicated fund; broad funds the user holds may already include the role at market weight. Use to answer 'what am I missing / what could I consider adding'. Deterministic; for the full per-candidate screen call screen_candidate.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`role`	No
`flavor`	No

Output Schema

TableJSON Schema

Name	Required	Description
`asof`	Yes
`gaps`	Yes
`note`	No
`unpriced_holdings`	No	held tickers with no cached price — role exposure (and thus the gaps) may be skewed; warm the cache for the full picture

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv2.12.1Jul 26, 2026

removedOutput schema / properties / note / default

Removed value: -"Roles your book holds ≤3% of, each showing its standard shelf's comparable funds — propose-only, never a prediction. `other_shelves` names sub-exposures not shown (treasury durations, sectors); picking a shelf is the user's decision. For the full screen (cost / liquidity / overlap / did-it-diversify-your-drawdowns) call `screen_candidate`. Read-only: figures are derived from your transaction log and the on-disk price cache. Uncached prices are fetched online on demand — a one-time core warm on the first cold call, plus any new ticker you ask about (set ASSET_MCP_OFFLINE=1 to keep it strictly offline); a value still unavailable shows null (n/a), never a guess. This is a view, not financial advice."

Changed8 schema fields changedv2.12.0Jul 22, 2026

addedInput schema / properties / flavor

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Flavor"
+}

addedInput schema / properties / role

Added value: +{
+  "anyOf": [
+    {
+      "enum": [
+        "us-large",
+        "us-small-mid",
+        "us-dividend",
+        "intl-developed",
+        "em-equity",
+        "sector-equity",
+        "bond-aggregate",
+        "treasury",
+        "tips",
+        "corporate-bond",
+        "gold",
+        "commodity-broad",
+        "reit"
+      ],
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Role"
+}

addedOutput schema / $defs / FlavorShelf

Added value: +{
+  "properties": {
+    "flavor": {
+      "title": "Flavor",
+      "type": "string"
+    },
+    "n": {
+      "description": "universe funds on this shelf (named, not screened)",
+      "title": "N",
+      "type": "integer"
+    }
+  },
+  "required": [
+    "flavor",
+    "n"
+  ],
+  "title": "FlavorShelf",
+  "type": "object"
+}

addedOutput schema / $defs / GapCandidate / properties / flavor

Added value: +{
+  "default": "",
+  "description": "the SHELF this fund sits on within its role (e.g. treasury duration, a sector) — a display/address label, never a recommendation; blank = the role's one unnamed shelf",
+  "title": "Flavor",
+  "type": "string"
+}

changedOutput schema / $defs / RoleGap / properties / candidates / description

Previous value: -"largest low-cost ETFs in this role, by AUM"New value: +"comparable funds from the role's standard shelf (its lead flavor), core funds first — a ≥3-way choice of near-substitutes, never a ranking"

addedOutput schema / $defs / RoleGap / properties / lead_flavor

Added value: +{
+  "default": "",
+  "description": "the shelf the candidates came from — the same shelf the presets buy from, so the default carries no new stance; blank for single-shelf roles",
+  "title": "Lead Flavor",
+  "type": "string"
+}

addedOutput schema / $defs / RoleGap / properties / other_shelves

Added value: +{
+  "description": "this role's OTHER shelves, named with counts but not surfaced — different exposures the user may deliberately choose (call again with role= and flavor= to see one); choosing between shelves is the user's decision, tell them these exist rather than picking for them",
+  "items": {
+    "$ref": "#/$defs/FlavorShelf"
+  },
+  "title": "Other Shelves",
+  "type": "array"
+}

changedOutput schema / properties / note / default

Previous value: -"Roles your book holds ≤3% of, with the biggest funds for each — propose-only, never a prediction. For the full screen (cost / liquidity / overlap / did-it-diversify-your-drawdowns) call `screen_candidate`. Read-only: figures are derived from your transaction log and the on-disk price cache. Uncached prices are fetched online on demand — a one-time core warm on the first cold call, plus any new ticker you ask about (set ASSET_MCP_OFFLINE=1 to keep it strictly offline); a value still unavailable shows null (n/a), never a guess. This is a view, not financial advice."New value: +"Roles your book holds ≤3% of, each showing its standard shelf's comparable funds — propose-only, never a prediction. `other_shelves` names sub-exposures not shown (treasury durations, sectors); picking a shelf is the user's decision. For the full screen (cost / liquidity / overlap / did-it-diversify-your-drawdowns) call `screen_candidate`. Read-only: figures are derived from your transaction log and the on-disk price cache. Uncached prices are fetched online on demand — a one-time core warm on the first cold call, plus any new ticker you ask about (set ASSET_MCP_OFFLINE=1 to keep it strictly offline); a value still unavailable shows null (n/a), never a guess. This is a view, not financial advice."

First observedv2.11.4Jul 17, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations already declare readOnlyHint=true and idempotentHint=true. The description adds further behavioral context: 'offline, read-only, propose-only', deterministic results, and specific edge-case behavior (sector-equity handling). No contradictions 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.

Conciseness4/5

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

The description is fairly long but each sentence adds value. It is front-loaded with the main purpose and then covers exceptions and usage details. Minor redundancy could be trimmed, but overall it is well-structured and informative.

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 that the tool has 2 optional parameters, no required ones, and an output schema exists (though not shown), the description covers all necessary aspects: what is returned (gaps with comparable funds, core funds first, other_shelves), how parameters affect output, and edge cases. Completeness is high.

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 has 0% description coverage, so the description must fully explain parameters. It explains `role` by listing the roles implicitly and noting special handling for 'sector-equity'. It explains `flavor` as 'add flavor= to see one shelf's funds'. This adds significant meaning beyond the schema's enum and default values.

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 clearly defines the tool's purpose: identifying portfolio gaps (roles ≤3% market value) and suggesting comparable funds from a standard shelf. It distinguishes itself by mentioning a sibling tool `screen_candidate` for further detail, and specifies what it does not do (e.g., flag sector-equity as a gap).

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 explicitly states when to use the tool: 'Use to answer what am I missing / what could I consider adding'. It also provides when-not-to-use guidance (sector-equity not flagged, calling with specific role to see shelf map) and notes that broad funds may already cover the role, giving the agent clear decision context.

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

Deploy Server