Ava Advisor

Screen Stocks

screen_stocks

Read-only

⭐ The cohort SCREENER: "which stocks in are interesting / winning / losing / most-talked-about, and how cheap or expensive do they trade?" Ranks the companies in a scope by how news is hitting them (lead with the winners-vs-losers split), and EVERY row carries its VALUATION (P/E, P/B, dividend yield, 52w) — so this is also the tool for "which in are cheap / worth investing" (pulse(kind='theme')/brief are news-only, no valuation — pull P/E from here; P/B leads for banks/insurers). ⚠️ Rows are a NEWS-RANKED, CAPPED SUBSET, not the full cohort — do NOT compute a sector/peer AVERAGE from them (biased sample). For "cheaper/richer than the sector average / below-above the group / undervalued vs peers" use screen_unified with a below_average/above_average pattern (proper cap-weighted, outlier-cleaned benchmark). Scope ≥1 REQUIRED (never whole-universe): megatrend / gics / country — combine freely. Each row = {symbol, name, country, gic_code, market_cap_usd, impact:{news_count, pos, neg, ambiguous, net_direction, top_relevance, aspects, top_reason}, fundamentals:{pe_ratio, pb_ratio, dividend_yield_pct, week52_high, week52_low}}; direction_split pre-tallies winners/losers. ⚠️ per-stock impact scoring exists only from ~2026-07-03 — an earlier window returns empty (say so, not "nothing happened"). One ticker → pulse(kind='asset'); a group's overall pulse → pulse(kind='theme'); a sector-average benchmark → screen_unified.

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": "screen_stocks"
  }
}

Input Schema

Name	Required	Description
`to`	No	Upper time bound, ISO date `YYYY-MM-DD`.
`gate`	No	megatrend scope only: `both` (default, strict member AND epicenter) \| `membership` (looser).
`gics`	No	A GICS sector/industry — a CODE PREFIX (sector `25` / group `2550` / industry `255010` / sub `25501010`, CSV for several) OR plain English ('banks', 'semiconductors', 'biotech'); the server resolves it. 🔴 ENGLISH (translate the concept first: ธนาคาร→'banks'). So 'European banks' = gics='banks' + country=EU codes.
`from_`	No	Start date YYYY-MM-DD. ⚠️ per-stock impact scoring only exists from ~2026-07-03 (earlier → empty).
`limit`	No	Max rows (default 20, hard cap 50). Keep SMALL + narrow the scope; page/refine rather than dump — heavily-covered assets have hundreds of articles.
`aspect`	No	Impact CHANNEL filter (e.g. `demand`, `competition`, `tariff`, `monetary`). Omit → all channels.
`window`	No	News-recency window: `7d`/`30d`/`90d`/`180d`/`1y` or `mtd`/`qtd`/`ytd`. Omit → a sensible default. (Price history is unaffected — this only scopes the NEWS lens.)
`country`	No	Market filter — CSV of ISO-2 codes (e.g. `US` or `CN,TW,HK`). 🌍 If the question names a NATIONALITY or REGION ('European','Thai','Chinese','ASEAN'), put it HERE — never leave it inside a concept/`q`/`gics` field. Enumerate a region into its member ISO-2s yourself (Europe→GB,DE,FR,IT,ES,NL,CH,SE; ASEAN→TH,SG,MY,ID,PH,VN).
`order_by`	No	`news_count` (default, most attention) \| `relevance` \| `market_cap`.
`direction`	No	`pos` → winners only · `neg` → losers/at-risk only · omit → all.
`megatrend`	No	A megatrend node — a name/slug (resolved for you, e.g. `foundry`) or an int node id. CSV for several.
`min_impact`	No	Min article importance, 1–5.
`min_relevance`	No	Min centrality to its news, 0–1.
`min_market_cap_usd`	No	Min market cap, USD.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 6, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations only declare readOnlyHint, and the description adds substantial context beyond that: rows are a news-ranked capped subset (biased sample), a minimum-scoring date of ~2026-07-03 that yields empty results for earlier windows, and that empty output should be reported as a data limitation rather than 'nothing happened'. Those are exactly the failure modes an agent would otherwise misread.

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 role and the winners-vs-losers framing before the caveats, and the row shape is compactly expressed inline. It is dense and long for a single description, with several ⚠️ blocks competing for attention, but nearly every line carries operational value.

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?

For a 14-parameter screener with no output schema, the description still specifies the full row payload (impact and fundamentals sub-objects), the direction_split pre-tally, and the scoring-availability cutoff. Nothing an agent needs to call it correctly or interpret results is missing.

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

Parameters5/5

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

Schema coverage is already 100%, yet the description still adds meaning: gics accepts English concepts that must be translated, region/nationality must go in country (enumerated into ISO-2s) rather than in gics or a concept field, megatrend/gics/country combine freely but at least one is required, and P/B is the lead valuation metric for banks. This is more than the schema conveys.

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 (ranks the companies in a scope by how news hits them) and names the exact output payload (valuation: P/E, P/B, dividend yield, 52w). It explicitly distinguishes itself from pulse(kind='theme')/brief (news-only) and screen_unified (benchmark), so an agent can pick it without opening any schema.

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

Usage Guidelines5/5

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

Gives when-to-use (winners/losers, cheap-vs-expensive in a group), explicit when-NOT (do not compute a sector average from these rows; use screen_unified with below_average/above_average for peer benchmarks), and full routing for adjacent questions (one ticker → pulse(kind='asset'), group pulse → pulse(kind='theme')). It also states the scope-≥1 hard requirement.

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

All Ava Advisor tools Inspect

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.