Skip to main content
Glama
Sign In

Qanvo Stock Screener

by app.qanvo
OverviewDiscussionsAdmin

Screen the market

market_query
Read-only

Screen global stocks (and crypto) with a natural-language question and get a typed dataset back. Examples: "quality large caps 15% below their 52-week high with IV rank above 60 and no earnings in 30 days", "wheel candidates with 30-delta put yield above 20% annualized", "software companies over $5B growing revenue 20%+". Returns the interpretation (how ambiguous terms were resolved), filter criteria, typed columns (with format hints: pct values are fractions, usd values are dollars), up to 200 rows, data as-of dates and warnings. Each call creates a saved research query; pass session_id to keep related queries together. You always get the full rows to analyze. Where the chat shows the interactive Qanvo Screener under the result, the user already sees every row there: give the takeaways rather than retyping the table. Where it doesn't, present the rows as usual. Research data only, not investment advice.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "prompt": "<prompt>"
    },
    "name": "market_query"
  }
}

Input Schema

NameRequiredDescriptionDefault
marketNoOptional market: an ISO country code such as US, GB, IN, JP or CN limits results to listings trading there (one listing per company). Omit for all markets.
promptYesThe market question in plain English.
session_idNoOptional session id from a previous result to group queries.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, non-destructive, non-idempotent), and the description adds real value beyond them: it discloses that each call creates a saved research query, that results are capped at 200 rows, and what metadata (interpretation, as-of dates, warnings) comes back. It stops short of stating any rate limits or latency behavior.

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 core purpose and examples before the return-value and presentation details. It is somewhat long, and the screener-presentation guidance is arguably user-facing policy rather than tool semantics, but no sentence is filler.

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-value burden and does so thoroughly: interpretation, filter criteria, typed columns with format hints, row cap, as-of dates, and warnings. Combined with 100% parameter coverage, an agent has everything needed to call it 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 100%, so market/prompt/session_id are already documented in the schema, and the description mostly restates them (session_id grouping, global vs. market scope). It adds no syntax or format detail for the prompt parameter beyond the examples.

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?

States a specific verb and resource: 'Screen global stocks (and crypto) with a natural-language question and get a typed dataset back.' The three worked examples make the scope concrete, and the name/behavior is clearly distinguishable from siblings like refine_market_query or browse_examples.

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?

Gives rich guidance on when to use it via concrete screening examples and explains how to present results depending on whether the chat renders the interactive screener. It never explicitly states when to prefer the sibling refine_market_query instead, which keeps it short of a 5.

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

All Qanvo Stock Screener toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources