Skip to main content
Glama

TejHQ Indian Markets

Unusual activity on a day

unusual
Read-onlyIdempotent

NSE stocks that did something far outside their own previous 60 sessions on one day, strongest first by abs(z). signal is one of volume, move, gap, delivery, fut_oi, high_52w, low_52w; value is what happened, normal what is usual for the stock, z the distance in standard deviations. Facts about the day, not forecasts or advice. date defaults to the latest day; meta.date is the day used. Returns 50 rows by default, up to 200. Coverage: NSE from 2010. Tier: needs a Retail or Pro key (https://tejhq.dev/upgrade).

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": "unusual"
  }
}

Input Schema

NameRequiredDescriptionDefault
dateNoTrading date. Default: latest. Format YYYY-MM-DD.
limitNoMost rows to return.
offsetNoRows to skip, for paging. Use meta.next_offset from a truncated result.
signalNoOnly this signal.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description layers on real behavior beyond them: result ordering, default and maximum row counts, server-resolved default date, the meta.date and meta.next_offset response fields, data coverage start, and an auth/plan requirement with a URL. That is exactly the kind of context annotations cannot express.

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?

A single dense paragraph that front-loads the definition and sort order, then defaults, paging, coverage and plan requirement — no filler sentences. The signal enumeration and field glossary are packed into comma splices, which is efficient but slightly harder to scan than a list.

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 return-shape burden and does it: it names the output fields (signal, value, normal, z), the ordering, the paging metadata, and the token/default rules. Coverage, auth tier and row caps round out everything needed to call this correctly on the first attempt.

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%, so the baseline is 3; the description earns an extra point by defining what each signal actually means and what value/normal/z represent in the returned rows (abs distance in standard deviations), plus the offset/paging contract. The date, limit and offset semantics are largely duplicated from the schema, so it does not reach the top.

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?

"NSE stocks that did something far outside their own previous 60 sessions on one day" names the resource, the anomaly criterion (60-session baseline, single day), and the sort order (abs(z), strongest first), so an agent knows exactly what comes back. It is not explicitly differentiated from the sibling unusual_history (which presumably covers multi-day windows); the "one day" phrasing implies it but never routes the agent.

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?

Operational guidance is strong: date defaults to latest, meta.date reports the day used, 50 rows default up to 200, and paging via meta.next_offset. It also states scope ("facts about the day, not forecasts or advice"), coverage (NSE from 2010) and the key tier needed. What's missing is any explicit when-not-to-use or referral to unusual_history for historical windows.

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.

Resources