EdgarStack

Find management guidance in SEC filings and check it against results

management_guidance_tracker

Read-onlyIdempotent

Two modes on management guidance disclosed in SEC filing MD&A:

mode="candidates" (default): scans the latest 10-K or 10-Q MD&A (Item 7 or Item 2) for sentences that may contain guidance. Returns verbatim, source-linked candidates labeled by fixed cue words and whether they contain numeric-looking values. Candidates are not confirmed guidance and may include false positives. limit 1–30 excerpts, default 20.
mode="vs_actuals": finds explicit annual revenue ranges or targets in recent 10-K MD&A and compares them with later SEC-reported annual revenue for the named fiscal year. Only dollar-denominated sentences with an explicit year are used; ambiguous, quarterly and non-revenue guidance is excluded, and an unavailable match is not treated as zero. filingsToInspect 1–10, default 8. Most companies give guidance in earnings releases and calls rather than 10-K/10-Q text, so empty results are common. Not financial advice.

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": "management_guidance_tracker"
  }
}

Input Schema

Name	Required	Description	Default
`mode`	No		candidates
`limit`	No	mode=candidates: maximum guidance candidate excerpts to return
`ticker`	Yes	US ticker symbol
`formType`	No	mode=candidates only	10-K
`filingsToInspect`	No	mode=vs_actuals: maximum recent 10-K filings to inspect

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.7/5.0

Behavior5/5

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

Goes well beyond readOnlyHint/idempotentHint by disclosing that candidates are unconfirmed and may be false positives and come labeled by fixed cue words with a numeric-looking flag. It also states matching rules for vs_actuals (dollar-denominated sentences with an explicit year only, unavailable matches are not zero) and warns of frequent empty results plus a not-financial-advice caveat.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the two-mode framing, then one bullet per mode carrying defaults, ranges and exclusions. No sentence is filler; even the closing caveats about sparse guidance and not-financial-advice serve agent decision-making.

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 return-shape burden and does so: candidates are verbatim, source-linked, cue-word labeled with a numeric flag; vs_actuals yields a guidance-vs-reported-revenue comparison. Combined with mode defaults and the sparse-results warning, an agent has everything needed to call it correctly.

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 80%, so mode, limit, formType and filingsToInspect are already documented. The description still adds meaning by tying limit to candidate excerpts, tying filingsToInspect to recent 10-Ks, and explaining that formType selects the Item 7 vs Item 2 MD&A scanned. ticker is only implicitly covered as the subject company.

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 for each of two modes: scanning latest 10-K/10-Q MD&A (Item 7/Item 2) for verbatim, source-linked guidance candidates, and finding explicit annual revenue ranges and comparing them to later SEC-reported revenue. An agent can tell exactly what the tool extracts and what it compares 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?

Declares the default mode and the conditions that select each mode, plus what each mode excludes (quarterly, ambiguous, non-revenue guidance). It also sets expectations that empty results are common because guidance usually appears in earnings releases and calls, which is effectively a when-not signal. It stops short of naming any sibling tool as an alternative.

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

All EdgarStack 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?