Skip to main content
Glama

AkkruData

by ai.akkrudata
OverviewDiscussionsAdmin

13F portfolio detail for one manager-quarter

get_institutional_portfolio
Read-onlyIdempotent

One manager x one calendar quarter: the 13F holdings detail rows, under a quarter header that repeats the snapshot numbers and carries the amendment archive (accessions, sec_locators, amendments_merged, prior_versions). Rows mix three kinds told apart by each row's type: positions (stock rows with shares, value, weight, rank, avg_price and quarter-over-quarter deltas), derivatives (put_call, notional_value_usd, underlying_price_implied) and exited (positions closed out this quarter — identity plus the closing deltas only). weight is a percent string with two decimals, e.g. "61.88%". Read warnings: they flag an amendment whose claimed action type differs from its actual action, unit-correction multipliers (see the unit_multiplier fields), CUSIP_CHANGE rows (see each row's predecessor_cusip and shares_before_cusip_change) and a quarter with no prior filed quarter to compare against (activity and the d* deltas are null there — not everything is new). 30 credits per page; an unknown manager (404 OWNERSHIP_MANAGER_NOT_FOUND) or a quarter with no data (404 OWNERSHIP_MANAGER_QUARTER_NOT_FOUND) is still charged. POST /api/v1/ownership/institutional-holdings/portfolio; FINANCIAL_API_DOCUMENTATION.md. The URL opens the filing's EDGAR index page; see the files listed there for full details.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cikNo13F filer CIK, digits verbatim. Provide exactly one of cik / name.
nameNoManager name, filed or normalized spelling; whitespace and case are ignored, otherwise the match is exact.
pageNo1-based page number (default 1).
typeNoOne of "positions" (stock rows), "derivatives" (option rows), "exited" (positions closed out this quarter). Omit for all three; each row carries its own type.
cusipNo9-character CUSIP to pin one security inside the quarter. Give cusip or ticker, not both.
tickerNoTicker to pin one security inside the quarter.
quarterYesCalendar quarter label YYYYQn, e.g. "2026Q1" (Q1=Mar 31, Q2=Jun 30, Q3=Sep 30, Q4=Dec 31).
sort_byNoOne of period, d_shares, ticker, issuer_norm, type. Omit for the filed row order.
activityNoAny of "NEW", "ADD", "REDUCE", "HOLD", "CUSIP_CHANGE". Unknown values are dropped with a warning. Exited rows carry no activity label.
restatedNoAny of "added", "modified", "cancelled" — rows changed by a merged amendment.
page_sizeNoRows per page, 1-100 (default 50).
sort_orderNo"desc" (default) or "asc".desc

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior5/5

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

Even though annotations already declare readOnlyHint, idempotentHint, and destructiveHint, the description adds substantial behavioral context: the shape of the quarter header, the meaning of _warnings, null deltas when no prior quarter exists, the 30-credits-per-page cost, and the fact that 404s are still charged. This goes well beyond the annotations.

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 dense but front-loaded with the core purpose, then efficiently organizes row types, weight formatting, warnings, costs, and errors. A few trailing references like "The URL opens the filing's EDGAR index page; see the files listed there for full details" are less actionable and slightly dilute an otherwise high-value definition.

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 complex tool with 12 parameters and no output schema, the description is exceptionally complete: it covers the response structure, row-type distinctions, warning cases, null-delta behavior, credit costs, error statuses, the HTTP endpoint, and external documentation. An agent has enough context to invoke the tool correctly and interpret likely failures.

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?

The schema describes every parameter with 100% coverage, including the cik/name exclusivity, type values, quarter format, and sort options. The description adds thematic context around row types and output fields, but it does not meaningfully extend the meaning of the input parameters beyond what the schema already provides.

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 immediately specifies "One manager x one calendar quarter: the 13F holdings detail rows", naming the exact resource and granularity with a clear verb implied by the tool name. It also details the three row kinds, which distinguishes the tool from search-oriented or aggregate institutional tools among the siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The scope is clearly implied by "One manager x one calendar quarter" and the 13F-holdings context, and the description explains the three row types and warning semantics. However, it never explicitly names when to use this tool versus siblings like search_institutional_holdings or get_initial_holdings_by_id, nor does it state when not to use it.

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

All AkkruData toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources