Skip to main content
Glama

TejHQ Indian Markets

Stock screener

screener
Read-onlyIdempotent

Filter every stock on one date by its daily metrics. filters maps column.op to a number, for example {"ret_21d.gt": 0.1, "pct_off_52w_high.gte": -0.05, "avg_turnover_20d.gte": 50000000}. Columns: adj_close, ret_1d, ret_5d, ret_21d, ret_63d, ret_126d, ret_252d, ret_ytd, high_52w, low_52w, pct_off_52w_high, pct_off_52w_low, avg_vol_20d, avg_vol_60d, avg_turnover_20d. Ops: gt, gte, lt, lte. Returns are fractions (0.1 means 10%). universe restricts to the point-in-time liquid100, liquid250 or liquid500 members. date defaults to the latest; meta.date is the day used. Returns 50 rows by default, up to 200. End of day data only, no intraday or live prices. Coverage: NSE from 2010-01-04, BSE from 2024-07-08. 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": "screener"
  }
}

Input Schema

NameRequiredDescriptionDefault
dateNoTrading date. Default: latest. Format YYYY-MM-DD.
limitNoMost rows to return.
orderNoasc or desc. Numeric columns default to desc.
offsetNoRows to skip, for paging. Use meta.next_offset from a truncated result.
filtersNocolumn.op to value, up to 10 filters.
sort_byNoSort column. Default symbol.
exchangeNoExchange. Default nse.
universeNoOnly members of this universe on that date.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, and the description still adds substantial behavior the annotations cannot convey: default and maximum row counts, that meta.date reports the trading day actually used, exchange-specific coverage start dates (NSE 2010-01-04, BSE 2024-07-08), the EOD-only limitation, and the Retail/Pro key requirement. These are exactly the operational facts that determine whether a call succeeds or returns misleading results.

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?

The structure is well front-loaded: purpose first, then filter syntax and examples, then column/op vocabularies, then units, universe, defaults, limits, coverage, and access tier. It is dense but nearly every clause carries information an agent needs. The column enumeration is long but justified because filter keys depend on it.

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?

For an 8-parameter, nested-object tool with no output schema, the description covers inputs, defaults, limits, coverage, and access requirements thoroughly. The main remaining gap is row shape — it never states which fields each returned row contains (symbol, the metric columns, etc.) or the sort direction default interaction, leaving the agent to infer the response payload.

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 above that by explaining what the filter object keys mean, giving three worked examples, listing valid ops, and clarifying that return columns are fractions (0.1 means 10%) — unit semantics the schema cannot carry. Universe is also explained as point-in-time membership rather than a static list. Paging behavior via offset is left to the schema's own description.

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?

The opening sentence states a specific verb and resource ('Filter every stock on one date by its daily metrics') and scopes it to a cross-sectional screen on a single trading date. The full column list makes the domain unmistakable. It stops short of naming a sibling (e.g. metrics for per-symbol history), so an agent must infer the boundary from context rather than being told.

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 concrete operating context: date defaults to latest, universe restricts to point-in-time liquid100/250/500 membership, results are capped at 50 by default and 200 maximum, and it is explicitly end-of-day only with no intraday or live prices. It also flags the tier/auth prerequisite. It does not explicitly say when another tool would be the better choice, which keeps it below a 5.

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