Clarifo

document_summary

Read-onlyIdempotent

Summarise or compare companies' annual / interim reports (Nordic HEL, STO and US NYSE, NASDAQ). Runs a Clarifo model, so it is not on every account; others get an informational message. Use instead of pulling a whole filing into context.

Modes:

"single" (default): structured, citation-anchored summary of one company's filing.
"compare": side-by-side comparison of two companies' filings, e.g. risk factors, AI exposure, dividend policy, segment performance.

The prose keeps [page_id: ...] markers as internal anchors. Never print a raw page_id or marker: replace each with the matching sources[] card's citation_markdown.

Args: company / year / quarter: Single mode (year omitted = latest). company_a, company_b (+ year_a, year_b, quarter_a, quarter_b): Compare. document_type: "annual" (default) or "interim" (with quarter 1-4). focus: Topic to emphasise, e.g. "AI risk factors". locale: "en" (default) or "fi".

Returns single: company, year, docid, summary, pages_used, truncated, sources, source_policy; compare: company_a, company_b, comparison, scope_note, coverage (coverage_warning), merged sources. Failures return error.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "document_summary"
  }
}

Input Schema

Name	Required	Default
`mode`	No	single
`year`	No
`focus`	No
`locale`	No	en
`year_a`	No
`year_b`	No
`company`	No
`quarter`	No
`company_a`	No
`company_b`	No
`quarter_a`	No
`quarter_b`	No
`document_type`	No	annual

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 9, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Annotations only cover the safety profile (read-only, idempotent); the description adds real behavioral context beyond that: model availability varies by account with an informational-message fallback, output prose contains internal citation markers that must be rewritten before printing, and results can be truncated with a coverage_warning.

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?

Well front-loaded with labeled Modes, Args, and Returns sections; each block serves a purpose. The citation-marker instruction is slightly verbose for a tool description but is operationally relevant to how the output must be used.

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?

Covers both modes, defaults, error return shape, and output fields (even though an output schema exists), which is more than adequate for a 13-parameter tool with mode-dependent semantics. The one real gap is behavior when the required-per-mode company argument is omitted in single mode.

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 0% schema description coverage across 13 parameters, the description carries the load and mostly delivers: it groups parameters by mode, gives defaults (mode=single, document_type=annual, locale=en), notes year omission means latest, and constrains quarter to 1-4 with interim. It never states the expected format for company identifiers, which is the main remaining ambiguity.

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 (summarise/compare annual and interim reports) plus the covered universe (Nordic HEL/STO, US NYSE/NASDAQ) and the two modes. It also explicitly contrasts itself with the alternative of pulling a whole filing into context, so an agent can place it 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?

Gives a clear use directive ('Use instead of pulling a whole filing into context') and explains the mode split for one company vs two. It does not address the obvious overlap with the compare_companies sibling, nor does it say when a filing should be fetched directly (e.g. full text needed).

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.