Skip to main content
Glama
stockscreen-mcp

stockscreen-mcp

audit_stocks

Read-only

Check a watchlist or holdings against preset screens in one call to see which screens each stock passes, which it nearly passes, and which rules a position fails today.

Instructions

Check a watchlist or holdings against the preset screens in one call: which screens each stock passes, and which it nearly passes.

Use it to review a list of stocks, find near misses, or see what a position fails today. Use get_stock for every field on one symbol, and run_screen to discover new candidates. A long list over every screen returns a lot of text, so pass a screens list when you only need some.

Each stock returns a snapshot, passes (screen ids in list_screens order, matching the website and get_stock's passes_screens), near_misses, and notes when there are any. The top-level screens list minus passes gives the failing ids. near_misses maps each screen the stock fails on exactly one of at least two rules to "field short_by N", or to the field alone when short_by is absent. It ignores how far short the stock is, so check short_by before calling one close. short_by is the positive distance between a failed numeric rule's bound and the stock's value (rs_rating 60 against a min of 70 is short_by 10); on a max rule it is how far the value is above the bound (ibd_group_rank 154 against a max of 40 is short_by 114); it is absent when the value is missing and on non-numeric rules. notes maps a screen to the reason when its rules alone don't explain the result: a failing optional rule group, or a disabled required group.

detail=True adds failed_rules: every failed rule for each failing screen. Any response over 80,000 characters of JSON is refused with an error that says how many symbols fit, so for detail pass fewer symbols or a shorter screens list.

Symbols absent from the market's scan are listed in not_found rather than raising an error.

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": {
      "symbols": "<symbols>"
    },
    "name": "audit_stocks"
  }
}

Input Schema

NameRequiredDescriptionDefault
detailNoAlso return every failed rule per screen under failed_rules. Responses over 80,000 characters are refused with a hint of how many symbols fit.
marketNoMarket code, e.g. US, HK, JP, IN, DE. See list_markets.US
screensNoPreset ids from list_screens to check; defaults to every screen in the market.
symbolsYesTickers to check in this market, e.g. a watchlist or holdings.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.2

TDQS

A4.4/5.0
Behavior4/5

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

Annotations only declare readOnlyHint and openWorldHint; the description adds substantial behavior beyond that — the 80,000-character response cap and its refusal behavior, the fact that unknown symbols go to not_found rather than raising an error, and the detail=True expansion into failed_rules. The extended short_by/notes explanation leans toward return-value documentation, but it discloses conventions an agent cannot infer from the read-only annotation.

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 purpose and routing before the output detail, and every paragraph addresses a distinct concern (usage, response shape, near-miss semantics, size limits, not_found). It is long and the short_by sign convention example could be tightened, but nothing is decorative.

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?

Covers the full calling surface for a read-only audit tool: what is compared, how passes/failing ids are derived, what near_misses and notes mean, when detail is worth the size cost, and what happens to unknown symbols. Nothing an agent needs to invoke or interpret it correctly is absent.

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 the schema already documents symbols, market, screens, and detail, including the 80k refusal note. The description adds only usage flavor for `screens` (passing a subset when full results are noisy) and repeats detail's cap behavior, so baseline 3 is appropriate.

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?

Opens with a concrete verb and resource: "Check a watchlist or holdings against the preset screens in one call," and states the exact output distinction (passes vs. nearly passes). It is immediately distinguishable from get_stock (single symbol fields) and run_screen (discovery), both named in the text.

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 explicit when-to-use cases (review a list, find near misses, see what a position fails today) and explicit alternatives with the condition that selects them: get_stock for every field on one symbol, run_screen to discover new candidates. It also advises passing a `screens` list when only some screens are needed, which is a real invocation-level decision.

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