Fortunest demo

Allocation

allocation

Read-onlyIdempotent

DEMO portfolio (synthetic, shared, read-only). Read ONE dimension of the portfolio's allocation — where the money is, and how far that is from the user's saved targets — instead of the whole context. dimension: assetClass, sector, region, currency, cap, type, account (default assetClass; there is no separate broker dimension — an account label IS its broker). depth (1-30, default 10) keeps the largest segments and groups the rest into other; a segment already named 'Other' is the app's own fold of its smallest segments. withTargets (default true) adds targetPct and driftPct in percentage points wherever the user has saved a target, and raises a target nothing matched so a 0% holding against a target is never invisible; targets exist for assetClass and sector only. weightBasis says what weightPct is a percent OF: 'portfolio' for every breakdown dimension, and 'accounts' for dimension=account, where the weights are a percent of the accounts' combined value (totalValue) because an asset held in no account is outside that split. Every value is in the display currency. pending names holdings whose market data has not landed — they are in no segment, so the split is not final while it is there. Describes the portfolio; never investment advice.

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": "allocation"
  }
}

Input Schema

Name	Required	Description	Default
`depth`	No
`dimension`	No
`withTargets`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 10, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations already cover safety (readOnly, idempotent, closed-world), yet the description adds substantial behavior: synthetic shared DEMO data, how `depth` folds the tail into `other`, how a pre-existing 'Other' segment differs from that fold, what withTargets injects and that it raises unmatched targets, and that `pending` means the split is not final. It also states the tool is descriptive, never advice.

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?

Front-loaded with scope, then parameters in order, with no filler sentences. It is a dense, semicolon-chained block that takes effort to parse, and the weightBasis explanation could be split for readability, but nothing is redundant.

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?

No output schema exists, and the description compensates by naming the return fields (weightPct, targetPct, driftPct, totalValue), their units, and the currency assumption. Caveats about pending data and the target-only dimensions cover the remaining ambiguity an agent would face.

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 0%, so the description carries the full burden and does: it enumerates all seven dimension values, states the default, explains depth's range/default and tail-folding, and explains withTargets' default, its scope (assetClass and sector only), and the exact fields it adds. It also defines weightBasis semantics per dimension, which is meaning the schema cannot convey.

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 ('Read ONE dimension of the portfolio's allocation') and immediately contrasts scope with 'the whole context', which routes the agent away from a broader context tool. The parenthetical 'where the money is, and how far that is from the user's saved targets' pins down the content returned.

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?

Gives clear usage conditions: pick one dimension instead of the whole context, targets exist only for assetClass and sector, and there is no separate broker dimension because an account label IS its broker. It stops short of naming the sibling to use for the full context, so the alternative is implied rather than explicit.

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

All Fortunest demo tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.