Skip to main content
Glama
cvm-mcp
by msperlin

get_dfp_notes

Read-only

Reads explanatory notes from a company's annual or quarterly CVM filing by year. Lists detected numbered notes when no note or page range is supplied.

Instructions

Read the explanatory notes of one company/year.

Without note and pages, lists the detected numbered notes (number, title, pages). The first call for a company/year downloads the filing PDF (~15 MB) and extracts its text; later calls read the local cache.

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": {
      "cvm_code": "<cvm_code>",
      "year": "<year>"
    },
    "name": "get_dfp_notes"
  }
}

Input Schema

NameRequiredDescriptionDefault
noteNoNumber of the note to read (omit to list the notes).
yearYesReference year of the filing (YYYY).
pagesNoRaw page selection of the PDF, e.g. '25' or '25-31'. Use it when the notes could not be split into numbered sections.
cvm_codeYesCVM code of the company.
data_typeNo'dfp' = annual, 'itr' = quarterly.dfp
max_charsNoCap on the returned text.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.2.0

TDQS

A4.1/5.0
Behavior4/5

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

Goes well beyond the readOnlyHint/openWorldHint annotations by disclosing the operational cost profile: the first call for a company/year downloads a ~15 MB PDF and extracts text, subsequent calls hit the local cache. That is exactly the latency/cost signal an agent needs before invoking. It does not describe failure modes when extraction or note splitting fails, which the schema hints at but the description leaves implicit.

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?

Three sentences, each earning its place: purpose, mode behavior, cost/caching. Front-loaded with the verb and resource, no filler or restatement of the title.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained, and the description covers the two invocation modes plus the expensive first-call behavior. The data_type switch to quarterly filings is left entirely to the schema, a minor gap for a tool whose name implies annual filings only.

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?

With 100% schema coverage the baseline is 3, but the description adds real semantic value by explaining the interaction of note and pages (both omitted = list mode), which no single parameter description conveys. It does not mention data_type (dfp/itr) or max_chars, though the schema documents both adequately.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Specific verb+resource: 'Read the explanatory notes of one company/year', which is concrete and distinct from a document or search tool. It does not name a sibling such as search_dfp_notes or get_dfp_document, so the agent must infer differentiation from scope alone.

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?

Clear mode-switching guidance: omitting note and pages yields a listing of detected numbered notes, supplying them reads one. This tells the agent how to sequence calls (list first, then read). It stops short of stating when to prefer this over sibling tools like search_dfp_notes.

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