Skip to main content
Glama

beatandraise.com SEC Filings

Get Institutional Holders

get_institutional_holders
Read-onlyIdempotent

Who holds a company, from 13F filings: how much of each share class institutions hold, and how that changed quarter by quarter. The company-side view of 13F; get_holdings is the manager side (what one institution owns).

Use it for questions like:

  • "What % of AMD do institutions hold, and how has it changed over the last 4 quarters?" -> quarters=4; read quarters[].share_classes[].pct_of_class.

  • "Is Baupost an investor in AMD?" -> holder="Baupost" (a name fragment or a filer CIK). holder.matched_filers says which filers the name matched (empty: no 13F filer has it), holder.positions each quarter's position, holder.not_held_in the quarters with none. With holder the response is lean unless detail="full".

  • "Who are the largest holders / who bought or sold most last quarter?" -> top_holders, biggest_buyers, biggest_sellers, largest_new_positions, largest_exits.

  • "Who owns more than 5%?" -> large_holders_5pct (latest 13D/13G per holder).

  • "Every holder, with last quarter's position" -> limit=500, then offset=next_offset while next_offset is present (quarters[0].holders says how many there are). Each row has prev_shares and change_shares.

  • "How big is the position for each manager?" -> each holder row carries book_value_usd (the manager's whole 13F for the quarter, as filed, options included) and pct_of_book; no need to call get_holdings per manager.

quarters[] is newest complete quarter first (the one still being filed is in_progress_quarter), each with holders, shares_held, value_usd and share_classes[] (per cover-page class: shares_outstanding, held_by_13f, pct_of_class), share_count_source and holders_url.

Report each share class separately; never add classes together. Caveats to state: 13F is as filed and not deduplicated, options are excluded, holdings can exceed 100% for heavily shorted stocks, and a "new position" may be a manager whose previous 13F was late. Cite share_count_source for share counts and holders_url for holdings.

Args: company: Ticker (e.g. "AMD") or CIK of the company being held (not of the institution); for a company name, get them from search_companies first quarters: Number of complete quarters, newest first (1-12, default 4) holder: Optional 13F filer to follow across the quarters: a name fragment ("Baupost", "Berkshire") or a CIK ("1061768") limit: Number of top holders to return for the latest quarter (1-500, default 25) detail: "lean" or "full". Default: lean when holder is given (just the holder's positions, share classes and sources), full otherwise (adds top holders, buyers, sellers, new positions, exits and 5%+ holders) ticker: Same as company (models often name it so) cik: Same as company offset: Skip this many top holders (paging; the response's next_offset gives the next page)

A ticker that cannot be tied to a company (an index option such as XSP, a former ticker) is not an error: the response has empty quarters and not_covered with the reason, and ticker_used_by names companies whose cover pages stated it.

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": "get_institutional_holders"
  }
}

Input Schema

NameRequiredDescriptionDefault
cikNo
limitNo
detailNo
holderNo
offsetNo
tickerNo
companyNo
quartersNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / offset
      Added value: +{
      +  "default": 0,
      +  "type": "integer"
      +}
  2. Changed7 schema fields changed
    • addedInput schema / properties / cik
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null
      +}
    • addedInput schema / properties / company / anyOf
      Added value: +[
      +  {
      +    "type": "string"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • addedInput schema / properties / company / default
      Added value: +null
    • removedInput schema / properties / company / type
      Removed value: -"string"
    • changedInput schema / properties / detail / anyOf
      Previous value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "type": "string"
      +  },
      +  {
      +    "type": "boolean"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • addedInput schema / properties / ticker
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null
      +}
    • removedInput schema / required
      Removed value: -[
      -  "company"
      -]
  3. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already cover safety (readOnly, idempotent, non-destructive, openWorld), yet the description adds substantial behavioral context: 13F is as filed and not deduplicated, options are excluded, holdings can exceed 100% for heavily shorted stocks, and a 'new position' may reflect a late prior filing. It also discloses non-error failure behavior (unmapped ticker yields empty quarters plus not_covered) and the in_progress_quarter distinction.

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?

Content is front-loaded (purpose and sibling contrast first, then use cases, then response shape, caveats, args) and every section is functional. It is nonetheless dense and long, with a heavy example list that could be trimmed without losing information.

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 an 8-parameter, zero-schema-coverage tool, this is complete: params, response fields, paging, caveats to state, and citation guidance are all present. The output schema exists, yet the description's explanation of quarters[]/share_classes[] adds real navigational value rather than repeating structure.

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

Parameters5/5

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

Schema description coverage is 0%, so the description must carry the full parameter burden, and it does: it documents all eight arguments including the company/ticker/cik aliases, the quarters range (1-12, default 4), the holder name-fragment-or-CIK dual form, limit bounds, detail's lean/full default logic, and offset paging tied to next_offset.

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 opening sentence names a specific verb and resource ('Who holds a company, from 13F filings') and immediately distinguishes the tool from its sibling: 'The company-side view of 13F; get_holdings is the manager side.' An agent can tell the two apart 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?

Guidance is explicit and question-driven, mapping five concrete user questions to the specific parameter/response field to use. It also states a when-not-to-use case ('no need to call get_holdings per manager') and routes company-name lookups to search_companies.

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