Skip to main content
Glama

Portfolio review

portfolio_review
Read-onlyIdempotent

Review a household's holdings against a target model or custom allocation. Returns value by asset class and account, allocation drift, single-stock concentration, tax-loss harvesting candidates, unrealized gains, stress tests, and an asset-location score with suggestions. Missing prices are fetched from live quotes.

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": "portfolio_review"
  }
}

Input Schema

NameRequiredDescriptionDefault
bandNoRebalancing band in percentage points (default 5): an asset class further than this from target is out of band.
modelNoTarget model portfolio: conservative (20% stocks), moderately_conservative (40% stocks), moderate (60% stocks), growth (75% stocks), aggressive (90% stocks). Default moderate. risk_profile_score maps a client to one.
pricesNoLatest price per share by symbol, e.g. {"VTI": 301.25}. CASH and money-market funds are priced at $1. Symbols without a price here are fetched from live quotes.
targetNoCustom target allocation in percent, totalling 100. Use instead of model.
holdingsNoHoldings as objects, instead of holdingsCsv. Up to 300 rows; one row per lot gives the best tax estimates.
holdingsCsvNoHoldings as CSV text in the LunaTerminal import format: a header row with at least symbol and shares; the full header is account,account_type,symbol,shares,cost_basis,asset_class,acquired. cost_basis is the row's total dollars, acquired is YYYY-MM-DD. Example: account,account_type,symbol,shares,cost_basis,asset_class,acquired Joint brokerage,taxable,VTI,120,24000,,2021-03-15 Joint brokerage,taxable,AAPL,150,18000,,2019-06-01 Joint brokerage,taxable,CASH,8000,8000,, Up to 300 rows and 128 KB. Send this or holdings, not both.
harvestMinimumNoSmallest unrealized loss in dollars worth listing as a tax-loss candidate (default 1000).
concentrationLimitNoFlag a single non-diversified holding above this % of the household (default 10).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / holdingsCsv / description
      Previous value: -"Holdings as CSV text in the afa import format: a header row with at least symbol and shares; the full header is account,account_type,symbol,shares,cost_basis,asset_class,acquired. cost_basis is the row's total dollars, acquired is YYYY-MM-DD. Example:\naccount,account_type,symbol,shares,cost_basis,asset_class,acquired\nJoint brokerage,taxable,VTI,120,24000,,2021-03-15\nJoint brokerage,taxable,AAPL,150,18000,,2019-06-01\nJoint brokerage,taxable,CASH,8000,8000,,\nUp to 300 rows and 128 KB. Send this or holdings, not both."New value: +"Holdings as CSV text in the LunaTerminal import format: a header row with at least symbol and shares; the full header is account,account_type,symbol,shares,cost_basis,asset_class,acquired. cost_basis is the row's total dollars, acquired is YYYY-MM-DD. Example:\naccount,account_type,symbol,shares,cost_basis,asset_class,acquired\nJoint brokerage,taxable,VTI,120,24000,,2021-03-15\nJoint brokerage,taxable,AAPL,150,18000,,2019-06-01\nJoint brokerage,taxable,CASH,8000,8000,,\nUp to 300 rows and 128 KB. Send this or holdings, not both."
  2. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), and the description adds a genuinely useful behavioral fact beyond them: 'Missing prices are fetched from live quotes', which tells the agent about outbound network lookups and how missing price data is resolved. It does not mention latency, quote-failure fallback, or any cost of the analysis, so it is strong but not exhaustive.

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?

Two sentences, zero filler: the first states the action and input choice, the second front-loads the complete output inventory and closes with the live-quote caveat. Nothing is repeated from the schema or annotations.

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 8 optional parameters, nested objects and no output schema, the description's return-value inventory is exactly the right compensation, and the live-quote note covers the main hidden dependency. What is missing is guidance on how the two holdings inputs interact at runtime (both omitted) and how the default model is chosen when neither model nor target is supplied.

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?

Schema description coverage is 100% and each parameter already carries rich inline documentation (band semantics, model equity percentages, CSV format example, assetClass split syntax), so the schema does the heavy lifting. The description only adds the model-vs-custom-allocation framing already present in the target parameter, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The first sentence gives a specific verb and resource ('Review a household's holdings against a target model or custom allocation'), and the output enumeration (drift, concentration, tax-loss candidates, asset-location score) makes the tool's remit concrete. It stops short of naming a sibling to contrast with (e.g. rebalance_plan), so differentiation is inferential rather than explicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: the reader infers this is the diagnostic/analytics pass that would precede a rebalance_plan, and the schema notes the model/target mutual exclusivity and that risk_profile_score maps a client to a model. The description itself states no when-to-use condition, no prerequisites (e.g. holdings required), and no when-not-to-use guidance.

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