Skip to main content
Glama
Sign In

EdgarStack

by com.edgarstack
OverviewDiscussionsAdmin

Map off-balance-sheet commitments and exposures from the latest 10-K

off_balance_sheet
Read-onlyIdempotent

Map a US company's off-balance-sheet commitments and exposures from its latest 10-K across 18 categories (purchase obligations, uncommenced leases, supplier finance, receivables sold, VIEs, equity-method investees, guarantees, letters of credit, loss contingencies, contingent consideration, multiemployer plans, unfunded commitments, dilution, credit facilities, environmental/ARO, remaining performance obligations). Returns: the latest 10-K; xbrl facts tagged in THAT filing only (each with magnitude: maximum / recorded / low / reference, plus prior year and change), with tags the issuer stopped using listed under historicalOnly (not current figures); the 10-K's notes and MD&A liquidity section, each scored by trigger phrases; short verbatim excerpts; and a coverage line per category (tagged / text_found / not_found — not_found is not evidence of none). Most items are disclosed only in note text, so after the default call, call again with sectionId for every section marked alwaysRead and for the top-ranked section (coverage[].topSections[0]) of each category the user cares about, and read that text before stating any amount that is not in xbrl. Long sections come in pages: pass offset = nextOffset to continue. 10-K filers only (no 20-F/40-F). No present-value or adjusted-debt calculations.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "ticker": "<ticker>"
    },
    "name": "off_balance_sheet"
  }
}

Input Schema

NameRequiredDescriptionDefault
offsetNoCharacter offset within the section; pass nextOffset from the previous page
tickerYes
sectionIdNoReturn one section's full text instead of the overview, e.g. 'note-14' or 'mdna-liquidity' (ids come from the overview's sections list)

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already cover read-only, idempotent, open-world, and non-destructive behavior. The description adds substantial context beyond them: xbrl facts are limited to that filing, historicalOnly tags are separated, sections are scored by trigger phrases, excerpts are verbatim, coverage flags do not mean absence, and pagination behavior is disclosed.

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-loads the resource, category scope, and return shape before moving into workflow and limits. It is appropriately sized for a complex extraction tool, though the single long paragraph could be easier to scan.

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 no output schema, the description explains the return payload, provenance caveats, coverage semantics, pagination, filing-type restrictions, and analytical limitations. An agent has enough information to call it correctly and interpret the results.

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 coverage is 67%, and the description adds meaningful selection semantics: use sectionId for every alwaysRead section and the top-ranked section per category, and continue long sections with offset=nextOffset. It also clarifies that ticker refers to a US 10-K filer, though it does not fully document every parameter independently.

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: mapping a US company's off-balance-sheet commitments and exposures from its latest 10-K across 18 enumerated categories. This is specific enough to distinguish it from general filing retrieval or financial-statement tools without needing to name siblings.

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 a clear post-call workflow: re-call with sectionId for alwaysRead sections and top-ranked sections, and paginate with offset=nextOffset. It also states important exclusions (10-K filers only, no present-value or adjusted-debt calculations). It does not name alternative sibling tools for reading filings, so it falls short of a 5.

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

All EdgarStack 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