Skip to main content
Glama

equibles

by io.github.daniel3303

Insider Sentiment Scores

GetInsiderSentimentScores
Read-only

Rank stocks by a peer-relative 0-100 insider-accumulation score over 90 days: net buyers, net shares bought as a percent of shares outstanding, and net buy value. It uses qualifying open-market Forms 4/5 purchases and sales; Form 3 establishes initial ownership, and disclosed Rule 10b5-1 trades are excluded. Filter for cluster buys or liquidity, request the bottom ranking for distribution, or pass ticker for one stock's factors and universe rank. Filters never renumber the universe rank. Use GetInsiderTransactions for the filings.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
bottomNoReturn the LOWEST-scored stocks instead — the heaviest peer-relative net insider selling — lowest score first.
offsetNoNumber of matching ranked stocks to skip before returning rows (default: 0; ignored for a single-ticker lookup).
tickerNoOptional stock ticker (e.g. NVDA): returns that one stock's score, factor breakdown, and rank within the scored universe instead of the leaderboard. The other filters do not apply to a single-ticker lookup.
maxResultsNoMaximum number of stocks to return (default: 25, highest score first; clamped to 1-200).
minMarketCapNoMinimum market capitalization in US dollars (e.g. 300000000 = $300M; default 0 = no floor). Stocks with an unknown market cap are excluded when set.
minSharePriceNoMinimum share price in US dollars (e.g. 5 = $5; default 0 = no floor). Stocks with an unknown price are excluded when set.
clusterBuysOnlyNoReturn only stocks flagged as cluster buys (three or more distinct insiders buying in the window).
minDollarVolumeNoMinimum trailing 3-month average daily dollar volume in US dollars (e.g. 5000000 = $5M/day; default 0 = no floor). Stocks with unknown volume are excluded when set.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed1 schema field changed
    • addedInput schema / properties / offset
      Added value: +{
+  "default": 0,
+  "description": "Number of matching ranked stocks to skip before returning rows (default: 0; ignored for a single-ticker lookup).",
+  "type": "integer"
+}
  2. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the read-only/destructive annotations, the description discloses substantive behavior: data source (qualifying open-market Forms 4/5), treatment of Form 3, exclusion of Rule 10b5-1 trades, and the non-obvious invariant that filters never renumber the universe rank. These are exactly the behavioral traits an agent needs to interpret results correctly.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

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

Three dense sentences front-load the core purpose and then add methodology, exclusions, modes, and an alternative tool without redundancy. Every clause adds information, and no space is wasted restating the title or annotation fields.

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 tool with no output schema and no required parameters, the description is suitably complete: it defines the score, source data, exclusions, filter behavior, rank invariant, ticker mode, and alternative for raw filings. An agent can select and invoke it correctly without needing additional context.

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

Parameters4/5

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

The schema already documents all eight parameters completely, so the baseline is 3. The description adds value by explaining non-obvious parameter interactions—ticker mode returns factors and rank, bottom ranking is for distribution, and filters do not renumber the universe rank—which go beyond the individual property descriptions.

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?

The description opens with a specific action and object: 'Rank stocks by a peer-relative 0-100 insider-accumulation score over 90 days' and lists the inputs to the score (net buyers, net shares bought %, net buy value). This clearly distinguishes it from the many insider-related siblings, and the closing pointer to GetInsiderTransactions reinforces what this tool is not.

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?

It identifies concrete usage modes: default leaderboard, bottom ranking, ticker lookup, and filtering by cluster buys or liquidity. It also names the explicit alternative for raw filings ('Use GetInsiderTransactions for the filings'). However, it does not discuss when to prefer GetInsiderOwnership or other insider siblings, so the guidance is clear but not fully exclusive.

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

All equibles toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

B3.4/5.0
Disambiguation4/5

Most tools have clearly distinct purposes, with detailed descriptions that cross-reference related alternatives. A few near-duplicate names could cause misselection, notably SearchDocument versus SearchDocuments and GetCftcPositioning versus GetLatestCftcPositioning.

Naming Consistency5/5

Tool names consistently follow a VerbNoun camelCase pattern: Get for retrievals, Search for discovery, List/Read for document access, and Add/Close/Remove/Update/Watch/Create/Delete for portfolio mutations. Despite the large count, there is no mixing of naming conventions or unpredictable verb styles.

Tool Count1/5

108 tools is an extreme surface area, far beyond the 3-15 well-scoped range and well past the 25+ threshold. Even for a broad financial data platform, this creates a heavy selection burden and substantial context overhead for agents.

Completeness4/5

The server covers an unusually wide domain: prices, fundamentals, SEC filings, options, insider activity, 13F holdings, short interest, macro data, funds, IPOs, and full portfolio lifecycle management. Notable gaps remain, such as a basic company profile/ticker-resolution tool, dividend history, and analyst estimates, so it is not a perfect 5.

Resources