Fortunest demo

Holdings

holdings

Read-onlyIdempotent

DEMO portfolio (synthetic, shared, read-only). Read the holdings table — the positions themselves — instead of the whole context. sort: weight (default), value, dayChange (today's money move), dayChangePct (today's move in percent), gainPct, gainAbs, loss (biggest losses first), name, symbol; order desc|asc overrides the sensible default for the key. limit is 1-50 (default 10) with offset/nextOffset paging. filter narrows by account label, assetClass (Equities, Bonds, Gold & commodities, Real estate, Crypto, Cash, Other), category, sector, region, currency, an explicit symbols list and minWeight (a PERCENT, so 5 means 5%). fields picks the row width: core (symbol, name, weightPct, value, dayChangePct, dayChangeAbs, totalGainPct, totalGainAbs, quantity, assetClass, sector, category, accounts), fundamentals (adds valuation, growth, fair value, analyst view), lots (adds open quantity, tax-free quantity and the next maturity) or all. Every field ending in Pct is a PERCENT (4.32 = 4.32%). total counts the filtered list, not the page. Positions under 0.1% of the portfolio have no row: smallHoldingsGrouped gives their count, value and combined weight; a filter by symbols, assetClass, category or sector also names the matching ones, with their category, under notListed — held, but without a row. 'Top 5 holdings' is one call: sort=weight, limit=5.

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": "holdings"
  }
}

Input Schema

Name	Required	Description	Default
`sort`	No
`limit`	No
`order`	No
`fields`	No
`filter`	No
`offset`	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 declare read-only, idempotent, closed-world, non-destructive behavior, and the description adds substantial context beyond that: the data is synthetic/demo and shared, positions under 0.1% are omitted but summarized via smallHoldingsGrouped and notListed, and total counts the filtered list rather than the page. Those are exactly the non-obvious traits an agent would otherwise get wrong.

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?

Purpose is front-loaded, then parameters are walked through in a compact semicolon-delimited run with zero filler sentences. It is dense and long, but nearly every clause adds a distinct fact; a bulleted parameter block would read faster than the prose flow.

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?

With no output schema and six parameters including a nested filter object, the description still covers everything an agent needs: sorting, paging, filtering, row width, percent semantics, and the small-holdings edge case that would otherwise look like missing data.

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 description coverage is 0%, so the description must carry the load, and it does: it explains each sort key's meaning (dayChange = today's money move, loss = biggest losses first), that order overrides the sensible default, that limit is 1-50 with default 10 and offset/nextOffset paging, every filter dimension, that minWeight is a percent, and the exact contents of each fields preset.

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 concrete verb and resource ('Read the holdings table — the positions themselves') and immediately scopes it against a broader alternative ('instead of the whole context'), which lets an agent distinguish it from whole-portfolio readers like get_core 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 Guidelines4/5

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

Gives clear context for use and a concrete workflow shortcut ('Top 5 holdings' is one call: sort=weight, limit=5), plus guidance on which fields preset to pick. It stops short of explicit when-not-to-use routing to the singular `holding` sibling or to tax_lots, so it is strong but not exhaustive.

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.