Skip to main content
Glama

Material guru moves, newest filing first, each with its verdict

guru_moves
Read-only

The Follow the Pros feed. Every material 13F move — new position, full exit, a share count that moved by 25%, or a position of $100M or more — ordered by the date the filing became public, with a deterministic verdict line on each row. The verdict is identical for every caller: it compares the price when the investor traded, the price now and Deep Values' intrinsic value band, and it never predicts a return or recommends an action. Every row carries the company's legal name beside the ticker (name, e.g. "Occidental Petroleum"), or null where we hold none — null rather than the ticker echoed back, so a caller can tell a real name from a placeholder. Rows whose EDGAR filing date we do not yet hold fall back to when the row reached us and say so with filed_at_known: false. (GET https://app.deepvalues.ai/api/v1/gurus/moves — 0.01 credits per call; works with no credentials up to 5 call(s)/day per address) Missing data? Call request_data.

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": "guru_moves"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
slugsNoComma-separated guru slugs; default is every guru.
filed_sinceNoOnly moves filed on or after this date. Poll with it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / filed_since / examples
      Added value: +[
      +  "2026-08-01"
      +]
    • addedInput schema / properties / slugs / examples
      Added value: +[
      +  "warren-buffett,li-lu"
      +]
  2. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Goes well past the readOnlyHint/openWorldHint annotations: it pins down the verdict as deterministic and identical for all callers, explicitly denies prediction or recommendation, explains the null-vs-ticker-echo convention for name, and flags the filed_at_known:false fallback with its cause. It also discloses cost (0.01 credits/call) and the credential-free limit of 5 calls/day.

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 feed's identity and the material thresholds, then rows/verdict, then edge cases, then cost and the escape hatch. Dense but nearly every clause carries information; the parenthetical HTTP/credits tail is reference material rather than prose clutter.

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?

No output schema exists, so the description carries the full burden of describing returns, and it does: row ordering, the verdict line, the name field's null semantics, and the filed_at_known flag. Combined with cost and rate-limit disclosure, an agent has what it needs to call this correctly.

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 67%, so the baseline is 3. The description adds polling guidance for filed_since and the all-gurus default for slugs, but says nothing about limit or its 200 ceiling, and adds no syntax detail for the comma-separated slug list.

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 the resource and the exact scope: material 13F moves with the four qualifying conditions spelled out (new position, full exit, 25% share-count change, $100M+ position), ordered by filing-public date. An agent can tell this apart from a holdings or portfolio sibling without opening a schema.

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?

Gives a concrete polling pattern for filed_since, states that slugs defaults to every guru, and routes the agent to request_data when data is missing. It stops short of naming when to prefer guru_portfolio or smart_money_changes, so the exclusion side is implied rather than stated.

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