Skip to main content
Glama

Regime Similarity Search

sv_similar
Read-only

Find the historical market states most similar to a ticker on a given date — k nearest neighbors in the 22-dimensional regime vector space across ~3M ticker-days (2014→present). Returns {ticker, date, similarity} triples. The query nobody else sells. Params: ticker (required), at YYYY-MM-DD (default: latest), k (default 15, max 200). Free with X-ORKID-API-Key or $0.02 USDC/call via x402.

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": {
      "ticker": "<ticker>"
    },
    "name": "sv_similar"
  }
}

Input Schema

NameRequiredDescriptionDefault
kNoNeighbor count, default 15, cap 200
atNoReference date YYYY-MM-DD (asof: last trading day ≤ at)
tickerYesReference ticker, e.g. "AAPL"

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, openWorldHint and destructiveHint=false, so the description's real value is the added context: result shape ({ticker, date, similarity} triples), dataset scope (~3M ticker-days, 2014→present), default behavior for 'at', and the auth/cost model (free with X-ORKID-API-Key or $0.02 USDC via x402). It does not cover failure modes such as an unknown ticker or a pre-2014 date, which keeps it below 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.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The core sentence is well front-loaded and dense with useful detail, but 'The query nobody else sells' is pure marketing filler and the trailing 'Params:' block largely restates schema fields. Roughly a third of the text does not earn its place.

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?

With no output schema, the description correctly compensates by naming the return shape, and it covers cost/auth and dataset bounds. For a read-only, three-parameter lookup this is close to sufficient; only edge-case behavior (invalid ticker, dates outside the 2014→present window, response size at k=200) is unaddressed.

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 ticker, at and k are already documented, establishing a baseline of 3. The description adds the 'default: latest' behavior for 'at' that the schema omits, but repeats k's default 15 / max 200 verbatim and does not clarify that k is typed as a string or how ties/similarity scale are defined.

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 ('Find the historical market states most similar to a ticker on a given date') plus the mechanism (k nearest neighbors in a 22-dimensional regime vector space over ~3M ticker-days from 2014). This is clearly distinguishable from siblings like sv_vectors (raw vectors) or sv_fsds, since it returns ranked analogs rather than the underlying data.

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

Usage Guidelines3/5

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

The use case (finding historical analogues) is implicit in the phrasing, and calling it 'the query nobody else sells' gestures at a niche, but there is no explicit when-to-use/when-not guidance and no routing to alternatives such as sv_vectors for the raw regime vector. An agent must infer the boundary itself.

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