Skip to main content
Glama

Fintel Discovery — Financial Intelligence for AI Agents

by io.github.findimitrov

Get 13F Holdings — Full Parsed Infotable

Get13FHoldings
Read-onlyIdempotent
    Fetch and parse the complete equity holdings table from a specific SEC 13F-HR
    filing. Any institution managing more than $100M in US equities must file
    quarterly — this reveals their exact portfolio positions.

    Returns one record per position:
      - name_of_issuer        — company name (e.g. 'APPLE INC')
      - cusip                 — 9-character CUSIP identifier
      - title_of_class        — share class (e.g. 'COM', 'ADR')
      - value_thousands       — market value in thousands USD
      - value_usd             — market value in USD
      - shares_or_principal   — number of shares (SH) or principal amount (PRN)
      - investment_discretion — SOLE, SHARED, or OTHER
      - put_call              — 'Put' or 'Call' for options; null for equities
      - voting_sole/shared/none — voting authority breakdown

    PRIMARY USE: Step 2 of institutional holdings workflow. Obtain cik and
    accession_no from SearchEdgar13F or GetEdgarCompanyFilings, then call this
    tool to get the actual positions.

    Use min_value_thousands to filter noise (e.g. 1000 = positions ≥ $1M).
    Use sort_by='value_desc' to see the largest positions first.
    Use limit (default 100) and offset for pagination — large filers can
    have 3,000+ positions. Check _has_more in the response to know if more
    pages exist.

    Source: SEC EDGAR Archives (13F infotable XML). No API key required.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
paramsNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnlyHint and idempotentHint, and the description adds meaningful behavioral context: it parses SEC EDGAR Archives 13F infotable XML, requires no API key, returns one record per position, and exposes pagination via _has_more. No contradiction with the annotations exists.

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?

The description is longer than average but well-structured with a purpose statement, a return-field list, and a usage section. It front-loads the most important context and every paragraph adds practical value. Minor redundancy exists with schema parameter descriptions, but overall it earns its length.

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?

Given the output schema and annotations, the description supplies the critical selection context: where identifiers come from, how the parsed result is shaped, how to filter and paginate, and the data source. It is complete for a fetch/parse tool, though a few auxiliary parameters receive no contextual guidance beyond the schema.

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 reported as 0%, so the description must carry the parameter semantics burden. It does explain cik, accession_no, min_value_thousands, sort_by, limit, and offset with examples and thresholds, but it does not cover several auxiliary parameters such as source_resource_id, wholesaler_ids, exclude_fillers, or additional_display_fields, leaving those to the schema or external conventions.

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 verb and resource: 'Fetch and parse the complete equity holdings table from a specific SEC 13F-HR filing.' It also lists the exact output fields and frames the tool as Step 2 of an institutional holdings workflow, which clearly distinguishes it from search/discovery siblings like SearchEdgar13F and GetEdgarCompanyFilings.

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?

The description explicitly says this is the primary Step 2 tool and directs the agent to obtain cik and accession_no from SearchEdgar13F or GetEdgarCompanyFilings before calling it. It also gives concrete guidance on filtering, sorting, and pagination. It does not explicitly state when not to use the tool versus alternatives, but the 'PRIMARY USE' framing makes the intended context clear.

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

All Fintel Discovery — Financial Intelligence for AI Agents 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

A3.9/5.0
Disambiguation4/5

Most tools target a distinct resource and action, with clear separation between search and detail tools (e.g., SearchIAPDFirm vs GetIAPDFirmDetail, SearchBrokerCheck vs GetBrokerCheckDetail). A few pairs like SearchBrokerCheck and SearchBrokerCheckFirm could cause momentary confusion, but descriptions clarify individual vs firm scope.

Naming Consistency4/5

The dominant pattern is consistent: Search* for discovery, Get* for retrieval, with CamelCase throughout. Minor deviations like LookupTicker and MapInstrumentIds introduce different verbs, and SearchBrokerCheck does not explicitly signal 'individual' unlike SearchBrokerCheckFirm, but the overall convention remains predictable.

Tool Count2/5

With 32 tools, the surface is quite heavy and exceeds the 25+ threshold for 'too many.' While the financial intelligence domain is broad, several search/detail pairs and overlapping data-source tools could be consolidated to reduce cognitive load for agents.

Completeness4/5

The toolset covers major workflows well: 13F holdings, fund fee comparison, advisor due diligence, macro data, price history, options, and identifier mapping. Minor gaps exist, such as no standalone real-time quote tool, no news/sentiment data, and no direct CUSIP-to-company-name search, but these are workable around.

Resources