Clarifo

fetch_edgar_filing_on_demand

Read-only

Fetch one US SEC 10-K or 10-Q directly from EDGAR as a transient last resort, only when search_filing_content (same company and year) returned nothing because the filing text is not indexed, and the question needs the filing text (a quote, a risk-factor paragraph). Never loop it over years (rate limit: 15/hour global, 3/hour per company). Not for numbers (use get_company_financials / get_financial_statement), not for 8-Ks (use company_events), not for Nordic filings. The result is not stored; a repeat call costs another slot.

Args: company: Name, ticker or CIK of a US filer. year: Calendar year the reporting period ended in. form_type: "10-K" (default) or "10-Q"; no other forms. quarter: Required for 10-Q: the CALENDAR quarter the period ends in (1 = Feb-Apr, 2 = May-Jul, 3 = Aug-Oct, 4 = Nov-Dec), not the fiscal label; Apple's fiscal Q1 (ends late December) is 4. query: Optional keywords; returns only sections containing them. Prefer it to keep the response small.

Returns company, filing (accession_number, form_type, filing_date, report_date, primary_document_url), sections[] (item_number, item_title, text) and meta (rate limits remaining, note). Failures return error (rate_limit_global, rate_limit_company, filing_not_found, unsupported_form_type, quarter_required_for_10q, not_a_us_filer, edgar_fetch_failed, ...) and detail.

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": {
      "company": "<company>",
      "year": "<year>"
    },
    "name": "fetch_edgar_filing_on_demand"
  }
}

Input Schema

Name	Required	Default
`year`	Yes
`query`	No
`company`	Yes
`quarter`	No
`form_type`	No	10-K

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 9, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations already declare read-only and open-world, but the description adds information they cannot carry: hard rate limits (15/hour global, 3/hour per company), non-persistence of results, the cost of a repeat call (consistent with idempotentHint=false), and the enumerated failure modes from rate_limit_global through edgar_fetch_failed. Nothing behavioral is left for the agent to discover by trial.

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 decisive constraint is front-loaded in the first sentence and the Args block is tightly written. The Returns paragraph restates information already conveyed by the output schema, which is mild redundancy in an otherwise dense, well-structured 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 five-parameter, rate-limited external-fetch tool this covers everything an agent needs: eligibility, exclusions, limits, quarter semantics, and error taxonomy. Return values are also present in the output schema, so nothing material is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the entire burden and does so for all five parameters, including the genuinely non-obvious one: quarter means the CALENDAR quarter the period ends in, not the fiscal label, with a worked Apple example. form_type's allowed values and query's size-reduction purpose are also spelled out.

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 ('Fetch one US SEC 10-K or 10-Q directly from EDGAR') plus an explicit scope ('transient last resort'), and names the sibling it is not (search_filing_content, get_company_financials, company_events). An agent can distinguish it from every nearby alternative without opening a schema.

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?

Gives both a positive trigger (only when search_filing_content for the same company/year returned nothing because the text is unindexed) and negative routing (not for numbers, not for 8-Ks, not for Nordic filings), plus an explicit anti-pattern ('never loop over years'). This is the when/when-not/alternatives pattern at full strength.

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

All Clarifo tools Inspect

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.