Skip to main content
Glama

Equibles

by io.github.daniel3303
OverviewDiscussionsAdmin

Institution Portfolio (13F)

GetInstitutionPortfolio
Read-only

View the tracked stock positions of a specific institutional investor from an SEC 13F-HR filing. Shows the largest positions by published value (default 20, max 500), with share counts, value, percent of tracked 13F value, and position count. Values normally use report-date closing prices, may fall back to filer values, and can be zero when unavailable. Coverage is limited to tracked U.S.-listed common stocks and related put/call positions; use position type before treating options as ownership. Use SearchInstitutions first when the name is ambiguous.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
offsetNoNumber of ranked holding rows to skip before returning rows (default: 0, clamped to 0-100000). For the next page, add the returned row count to the clamped current offset; if the next offset exceeds 100000, narrow the filters instead. Stop when fewer than the effective page size (maxResults clamped to 1-500) are returned, or the response's total has been reached.
maxResultsNoMaximum number of holdings to return (default: 20, clamped to 1-500)
reportDateNoQuarter-end 13F report date in YYYY-MM-DD format (defaults to the holder's latest; an off-quarter date snaps to the nearest report on or before it)
institutionNameYesInstitution name or SEC CIK. A unique partial name resolves; an ambiguous partial returns candidate CIKs instead of selecting silently.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / offset / description
      Previous value: -"Number of ranked holding rows to skip before returning rows — pass the previous call's last row number to page past the maxResults cap (default: 0)"New value: +"Number of ranked holding rows to skip before returning rows (default: 0, clamped to 0-100000). For the next page, add the returned row count to the clamped current offset; if the next offset exceeds 100000, narrow the filters instead. Stop when fewer than the effective page size (maxResults clamped to 1-500) are returned, or the response's total has been reached."
  2. Changed1 schema field changed
    • changedInput schema / properties / institutionName / description
      Previous value: -"Institution name, partial name, or SEC CIK to search for"New value: +"Institution name or SEC CIK. A unique partial name resolves; an ambiguous partial returns candidate CIKs instead of selecting silently."
  3. Changed1 schema field changed
    • addedInput schema / properties / offset
      Added value: +{
+  "default": 0,
+  "description": "Number of ranked holding rows to skip before returning rows — pass the previous call's last row number to page past the maxResults cap (default: 0)",
+  "type": "integer"
+}
  4. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world). The description goes further by disclosing value provenance ('report-date closing prices, may fall back to filer values, and can be zero when unavailable') and a coverage boundary ('U.S.-listed common stocks and related put/call positions'), which are non-obvious data-quality caveats an agent needs.

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-loads the core purpose in sentence one, then layers return shape, value caveats, coverage limits, and routing advice. Dense but every sentence carries information; slight compression makes it read as one block rather than scannable clauses.

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?

There is no output schema, so the description carries the burden and does: it enumerates the returned fields (share counts, value, percent of tracked 13F value, position count) and flags the value-unavailable and options-interpretation cases. Nothing essential for correct invocation is missing.

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 100%, so the schema already documents offset, maxResults, reportDate, and institutionName in detail, including pagination arithmetic. The description merely restates defaults (20/500) and ranking order, adding no new parameter meaning beyond the schema baseline.

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?

States a specific verb and resource ('View the tracked stock positions of a specific institutional investor') plus the exact data source ('SEC 13F-HR filing'). This framing lets an agent separate it from stock-centric siblings like GetTopHolders and aggregate siblings like GetInstitutionConsensusHoldings without opening the 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 one explicit prerequisite ('Use SearchInstitutions first when the name is ambiguous') and cautions on interpreting put/call rows. It does not, however, say when to prefer this over CompareInstitutionPortfolios, GetInstitutionSummary, or GetTopHolders, so sibling routing is left partly to inference.

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

All Equibles 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