Skip to main content
Glama

Kaleidoscope MCP (SEC & financial data)

Semantic Filing Search

semantic_search
Read-onlyIdempotent

Find SEC filing SUB-SECTIONS semantically similar to a natural-language query (learned-sparse retrieval over the sub-section graph — Item 1A Risk Factors, Item 7 MD&A, Business, etc.). Unlike get_sentences (which filters by a known classifier name), this understands meaning: e.g. 'supply chain disruptions', 'interest rate sensitivity', 'workforce restructuring and severance'. Returns whole coherent sub-sections (more context than a single sentence). Optional filters: ticker, form ('10-K'/'10-Q'/'S-1'/'20-F'), sic, years, filed_before.

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": {
      "query": "<query>"
    },
    "name": "semantic_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
sicNoLimit to companies with this SIC code (optional)
formNoLimit to a filing form type: '10-K', '10-Q', 'S-1', '20-F' (optional)
limitNoMax results to return (default: 10, max: 25)
queryYesNatural-language query describing the filing language to find
yearsNoFiling years to search, e.g. [2025, 2026]. Default: all available years.
tickerNoLimit to a specific company ticker (optional; resolved to CIK)
filed_beforeNoRestrict to sub-sections whose filing_date <= this YYYY-MM-DD (point-in-time replay cutoff).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already carry readOnly, idempotent, non-destructive and closed-world, so the safety profile needs no restating. The description adds real behavioral context beyond that: retrieval is semantic rather than classifier-matched, and results are whole sub-sections rather than single sentences. It does not discuss ranking behavior or result ordering, which keeps it from a 5.

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 verb and resource, and the parenthetical retrieval detail earns its place by explaining why results differ from keyword or classifier search. Slightly dense, with a stacked clause of filters at the end, but no sentence is filler.

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?

There is no output schema, and the description does compensate by saying results are whole coherent sub-sections with more context than a sentence. What an agent gets back is clear in shape, though exact returned fields and ordering are not stated, which is a minor residual gap for a search tool.

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 description coverage is 100%, so every parameter is already documented, including the limit ceiling and the point-in-time meaning of filed_before. The description restates the filter set (ticker, form, sic, years, filed_before) and adds only the flavor of example queries. Baseline 3 applies when the schema does the heavy lifting.

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?

Names a specific verb (find), a specific resource (SEC filing sub-sections), and the mechanism (learned-sparse retrieval over the sub-section graph) with concrete section examples (Item 1A, Item 7). It also explicitly distinguishes itself from get_sentences, so an agent can route without opening either 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?

States the selection rule against the named sibling: get_sentences is for a known classifier name, this is for meaning-based lookup, and it supplies sample queries to make the distinction concrete. Nothing about when to choose this path is left to inference.

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