SEC Filings

Read one section across companies

read_section_across_companies

Read-onlyIdempotent

Use when someone asks what several companies say in the same section of their latest filing of one form, such as the risk factors in the latest 10-K of each company in a list. Takes up to 25 tickers or CIKs, a form and a section id. Returns, per company, a status (ok, unknown_ticker, no_filing, no_section or error), the filing id, dates and SEC source, and an excerpt of the section, with up to 24,000 characters shared across the companies and a flag that marks a cut. It needs a paid plan key and consumes one call per company.

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": {
      "tickers": "<tickers>",
      "form": "<form>",
      "section": "<section>"
    },
    "name": "read_section_across_companies"
  }
}

Input Schema

Name	Required	Description
`form`	Yes
`section`	Yes	A section id such as item-1a, item-7 or item-1.
`tickers`	Yes	Tickers in EDGAR spelling (BRK-B; BRK.B and BRK/B also work), or CIKs such as 320193.
`max_characters`	No	Characters of section text in the whole reply, shared evenly across the companies found.

Output Schema

Name	Required	Description	Default
`form`	No
`calls`	No
`count`	No
`error`	No
`items`	No
`usage`	No
`status`	Yes
`api_url`	No
`message`	No
`section`	No
`docs_url`	Yes
`duplicates`	No
`http_status`	No
`retry_after`	No
`details_dropped`	No
`characters_per_company`	No

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 6, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Beyond the readOnly/openWorld/idempotent annotations, it discloses the paid plan key requirement, that each company consumes one call (a cost model the agent must budget for), the per-company status vocabulary for partial failures, and a truncated excerpt with a cut flag. These are exactly the operational facts annotations cannot convey.

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?

Three sentences, front-loaded with the usage trigger, then inputs, then returns and cost. The return-value enumeration (statuses, filing id, dates, source, excerpt) is somewhat redundant given an output schema exists, but it is compact and readable.

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 multi-ticker fan-out tool with partial-failure modes, the description covers the scenario, input limits, cost per company, auth requirement, and truncation behavior. An agent has everything it needs to decide to call it and to interpret degraded 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 75%, and the description reinforces the key constraints (up to 25 tickers or CIKs, one form, one section id) and frames max_characters as a budget shared across companies, which shapes how an agent sets it. It omits the default (12000) and minimum (500), so it adds guidance rather than full semantics.

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 with explicit multi-company scope: 'what several companies say in the same section of their latest filing of one form', with a concrete example (risk factors across latest 10-Ks). This clearly separates it from the single-filing sibling read_filing_section and from compare_filing without opening either 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?

The opening 'Use when...' clause gives a clear triggering scenario, and 'several companies' implicitly excludes single-company lookups. It never names the alternative tools (read_filing_section, compare_filing) or states when not to use it, so routing is inferable but not explicit.

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

All SEC Filings 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.

Resources

Need Help?