Fintel Discovery — Financial Intelligence for AI Agents

Get Fund Expense Ratios — XBRL rr: Taxonomy

GetFundFees

Read-onlyIdempotent

    Retrieve expense ratios and fee breakdown for a mutual fund or ETF using
    its SEC CIK. Reads structured XBRL data filed with prospectuses using the
    SEC Risk/Return (rr:) taxonomy. Returns:
      - net_expense_ratio    — total annual cost to the investor (%)
      - gross_expense_ratio  — before waivers/reimbursements (%)
      - management_fee       — advisor/sub-advisor fee (%)
      - distribution_12b1_fee — distribution and service fee (%)
      - other_expenses       — admin, custody, transfer agent fees (%)
      - acquired_fund_fees   — fees from underlying funds, if any (%)

    All values are expressed as percentages (e.g. 0.03 = 0.03%).

    PRIMARY USE: Step 2 of fee comparison. Accepts CIKs returned by
    SearchFundsByCategory. Run for multiple funds then rank by net_expense_ratio
    ascending to find the lowest-cost option in a category.

    With include_all_classes=True (default), returns one row per share class
    per period — useful for identifying the cheapest share class of a fund.
    With include_all_classes=False, returns the single most recent value only.

    Note: Not all funds file XBRL rr: data. If this tool returns an error,
    use GetFundProfile (yfinance) as a fallback for expense ratio data.

    Source: SEC EDGAR XBRL company facts API. No API key required.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`params`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

TDQS

A4.6/5.0

Behavior4/5

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

Annotations already carry readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered and the bar is lower. The description adds genuinely useful behavior beyond annotations: the data comes from SEC EDGAR XBRL company facts with no API key, all values are expressed as percentages (including the 0.03 = 0.03% example), include_all_classes changes row cardinality, and the rr: taxonomy coverage caveat is disclosed. Minor gap: no rate-limit or error-shape detail, but this is modest for a read-only lookup.

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 long but deliberately structured: a field bullet list, a 'PRIMARY USE' block, an include_all_classes explanation, a fallback note, and a source line. It is front-loaded with the verb+resource in the first sentence, and each section adds information an agent needs. It is slightly longer than the minimum, but the length is justified by the tool's nuance rather than padding.

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 read-only tool with rich annotations and an output schema, the description covers everything needed to select and invoke it correctly: return fields with units, workflow position, input provenance, share-class behavior, data-availability caveat, fallback path, source, and authentication requirement ('No API key required'). There is no material gap for an agent to trip on.

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?

Schema description coverage is reported at 0%, so the description must compensate for parameter meaning. It does for the two tool-specific parameters: CIK is contextualized as the output of SearchFundsByCategory, and include_all_classes is explained with concrete behavioral consequences (one row per share class per period vs. single most recent value). The generic plumbing parameters (wholesaler_ids, source_resource_id, exclude_fillers, etc.) are not covered in the description, though they carry detailed schema descriptions of their own.

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: 'Retrieve expense ratios and fee breakdown for a mutual fund or ETF using its SEC CIK,' and identifies the data source (SEC XBRL rr: taxonomy). It differentiates from the 30+ siblings by naming its workflow partners explicitly — SearchFundsByCategory produces the CIKs it consumes, and GetFundProfile is the fallback — so an agent can disambiguate without opening schemas.

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?

Explicitly positions the tool in a workflow: 'PRIMARY USE: Step 2 of fee comparison. Accepts CIKs returned by SearchFundsByCategory,' with a concrete ranking instruction (rank by net_expense_ratio ascending). It also gives an explicit when-not and alternative: 'Not all funds file XBRL rr: data. If this tool returns an error, use GetFundProfile (yfinance) as a fallback.' This is the gold standard for usage guidance.

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 tools Inspect

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

Need Help?