kite-connect-mcp

Positions

get_positions

Read-onlyIdempotent

Fetch current net and day positions with quantities, prices, P&L, and buy/sell totals to review exposure and calculate intraday profit or loss.

Instructions

Short-term positions (derivatives and intraday equity). net is the actual current position book; day is a snapshot of today's buying and selling, useful for intraday P&L. Each position has tradingsymbol, exchange, product, quantity, overnight_quantity, multiplier (lot-size multiplier for P&L: 1 for equity and F&O, the lot size for MCX), average_price, last_price, value, pnl, m2m, unrealised, realised and the buy / sell / day_buy / day_sell quantity, price and value. A summary per book totals pnl, m2m, unrealised and realised (INR) and counts the open positions (quantity not 0). Equity positions carried overnight move to the holdings the next day.

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": "get_positions"
  }
}

Input Schema

Name	Required	Description	Default
`kind`	No	net: the actual current positions. day: today's buying and selling. both (default)	both

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 6, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the safety profile is covered. The description adds genuinely non-obvious behavior: the exact position record shape (including the `multiplier` lot-size quirk for MCX versus 1 for equity/F&O), that `summary` is computed per book and counts only positions with non-zero quantity, and that overnight equity migrates to holdings — none of which is in the annotations or schema.

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 scope and the net/day distinction, then the field inventory. The long field enumeration is dense but earns its place because there is no output schema; only the buy/sell/day_buy/day_sell trio is slightly verbose.

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 no output schema, the description appropriately documents the return shape, the per-book summary semantics, and the holdings hand-off. Minor gaps remain — it does not say what an empty book returns or whether results are paginated — but nothing needed to invoke the tool correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the enum already carries a short gloss for `net`/`day`/`both`, so the baseline is 3. The description goes slightly beyond by framing `day` as an intraday P&L snapshot and `net` as the actual book, which tells the agent which mode answers which question rather than just restating the enum.

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 opens with a specific resource and scope: short-term positions covering derivatives and intraday equity, then splits that resource into two named books (`net` = current position book, `day` = today's buying/selling). The closing sentence distinguishes it from the sibling `get_holdings` by explaining that overnight equity positions move to holdings the next day, so an agent can route between the two without opening either 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?

It gives clear context for each mode — `net` is the actual position book, `day` is for intraday P&L — and implicitly excludes overnight equity via the holdings pointer. It stops short of an explicit "use get_positions when X, use get_holdings when Y" rule, so the agent must infer the boundary from the last sentence.

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