Skip to main content
Glama

portfolios

Read-onlyIdempotent

The user's own Clarifo portfolios (watchlists and investment portfolios).

Without portfolio_id: the list, with company counts. With portfolio_id: its companies with notes and positions, each company's share price change over period and latest reported fiscal year, signals, recent and upcoming reports, and the user's own analyses of the companies (read one with get_workspace_item; view="since" says how a company has done since). An investment portfolio also gets performance for year, or start_date to end_date (default this year to date): realized gains and losses, dividends, fees, profit and money-weighted return, in currency. Read-only.

Args: portfolio_id: From the list; omit to list portfolios. period: Price-change window: 1M, 3M (default), 6M, 1Y, YTD. chart: Leave False. The Clarifo panel sets it to draw price lines (price.series, index 100 at the period start). year: Calendar year for performance, e.g. 2025. start_date: Performance from this date (YYYY-MM-DD); not with year. end_date: Performance to this date (YYYY-MM-DD, default today). currency: ISO code for performance totals (default the portfolio's display currency). signals: "latest" (default: each company's newest period), "all" (every stored period) or "none". following: True for the companies the user follows (the Follow button) instead: {"following": [{"company_name", "ticker", "price"}]}, price change over period. Not a portfolio.

Returns: {"portfolios": [{"portfolio_id", "name", "type", "company_count", "workspace_id", "workspace_name"}]} or {"portfolio_id", "name", "type", "workspace_id", "companies": [{"company_id", "company_name", "ticker", "position", "price", "latest_fy"}], "position_totals" (value, cost, unrealized result and currency_mix in the display currency), "signals", "events", "own_research", "ledger_positions", "ledger_totals" (per cost currency), "performance"}. Give company_id to get_company_snapshot.

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": "portfolios"
  }
}

Input Schema

NameRequiredDescriptionDefault
yearNo
chartNo
periodNo3M
signalsNolatest
currencyNo
end_dateNo
followingNo
start_dateNo
portfolio_idNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnlyHint/idempotentHint/openWorldHint=false, and the description confirms "Read-only" while adding real behavioral context the annotations don't carry: default period (3M), default performance window (this year to date), default display currency, and that `chart` is set by the Clarifo panel rather than the agent. It doesn't mention pagination or result-size limits, which is the main remaining gap.

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 the purpose and mode split, then a clearly segregated Args block. It is longer than typical, and the Returns paragraph largely restates an output schema that already exists, which is the main place wording could be trimmed; the Args notes themselves are dense and earn their space.

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 nine-parameter, dual-mode tool with an output schema, the definition covers mode selection, defaults, parameter interactions, and where to go next for company-level detail. Nothing an agent needs in order to call it correctly appears to be missing, and the return-shape paragraph, while partly redundant, disambiguates the two response variants.

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 carries the full burden and does: every one of the nine parameters is explained with meaning, allowed values, and defaults (period 1M/3M/6M/1Y/YTD, signals latest/all/none, ISO currency defaulting to display currency, YYYY-MM-DD date formats, end_date default today). It also states inter-parameter constraints (start_date not with year) and the non-obvious meaning of `following` and `chart`, which no structured field conveys.

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 opening sentence names the exact resource and its two subtypes ("The user's own Clarifo portfolios (watchlists and investment portfolios)"), and the following sentences split the behavior into list mode vs. portfolio_id detail mode. This is clearly separable from siblings such as get_company_snapshot or get_workspace_item, which are named as destinations for sub-reads.

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?

Concrete routing rules are given: "Without portfolio_id: the list... With portfolio_id: its companies", "omit to list portfolios", "read one with get_workspace_item", "Give company_id to get_company_snapshot", and "chart: Leave False". It also states a constraint ("start_date ... not with year") and that `following` is "Not a portfolio". It stops short of stating when not to use this tool overall, 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.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.