kite-connect-mcp

Alerts

get_alerts

Read-onlyIdempotent

Retrieve your Kite alerts newest first, with optional status filtering and limit/offset pagination, so you can review enabled, disabled, or deleted alerts.

Instructions

Your alerts, newest first. Kite allows at most 500 active alerts per user. Each has uuid, type (simple or ato), name, status (enabled = being evaluated, disabled, deleted = soft-deleted), disabled_reason, the condition (lhs_exchange, lhs_tradingsymbol, lhs_attribute, operator, rhs_type, rhs_constant or the rhs_* instrument), alert_count (how many times it triggered), created_at / updated_at (IST) and, for an ato alert, the basket of orders it places.

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_alerts"
  }
}

Input Schema

Name	Required	Description
`limit`	No
`offset`	No
`status`	No	only alerts in this state (enabled, disabled, deleted); omit for the default list

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 6, 2026

TDQS

A3.6/5.0

Behavior4/5

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

Annotations already establish this as a safe, idempotent read, and the description adds real context beyond them: the 500-alert-per-user ceiling, that "deleted" means soft-deleted (so filtering still returns records), that status enabled means actively evaluated, and that timestamps are IST. These details materially affect interpretation of results but are not in the annotations.

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 in the first clause, followed by the constraint and then the field inventory. The field list is a single run-on sentence, but every item earns its place given there is no output schema to document the response shape.

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, the description carries the full burden of describing the returned alert object, and it does so field by field, including the ato variant's order basket. Combined with the 500-alert cap, ordering, and soft-delete semantics, an agent has what it needs to call and interpret the result.

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 coverage is only 33%, with limit and offset carrying no descriptive text anywhere. The description partially compensates by defining the three status values it will filter on (enabled = being evaluated, disabled, deleted = soft-deleted), which gives the status parameter meaning, but pagination semantics remain undocumented.

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?

"Your alerts, newest first" names the resource (alerts), the owner scope (your), and the ordering, so an agent knows this is a list operation. It does not distinguish itself from the sibling singular get_alert or from get_alert_history, so an agent must infer which of the three to call.

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

Usage Guidelines2/5

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

There is no explicit when-to-use guidance: nothing says to use this for browsing/filtering all alerts versus get_alert for one by uuid or get_alert_history for past triggers. The only usage-shaped hint is the status filter documented in the schema, not the description.

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