Skip to main content
Glama
NewsCatcher MCP

NewsCatcher MCP

Official

Get research results

get_research
Read-onlyIdempotent

Retrieve the status and results of a research run: tables with source links, company coverage, or cited briefings. Call without a run ID to list your recent runs.

Instructions

Status and results of a research run from start_research: waits (up to wait_seconds) while it runs, then returns the table (columns + rows with source links), each company's coverage for company runs, and the cited briefing for Standard/Max runs. Call it with no run_id to list your recent runs (ids, status, titles). Free.

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": "get_research"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNoWhen listing: only runs of this kind.
sortNoRow order: original (as the run returned them), newest or oldest first by the row's date column, or importance (most important first, then newest). Row numbers (#) stay the run's own.original
limitNoWhen listing: how many recent runs.
formatNotext (default) or json.text
run_idNoThe run to read. Leave out (and batch_id too) to list your recent runs.
batch_idNoA batch (a company list split over several runs) instead of a run.
rows_limitNoRows to show (default 25, max 200). Page with rows_offset.
rows_offsetNoFirst row to show (for paging through a big table).
exclude_rowsNoRow numbers (#) to leave out after checking (duplicates, out of scope): the table and the counts line then cover only the kept rows.
wait_secondsNoIf the run is still going, wait up to this many seconds for it to finish (default 30; use 120–300 for long runs; 0 = status now).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already mark it read-only/open-world/idempotent, but the description adds genuinely new behavior: it can block for up to wait_seconds while a run executes, it returns source-linked rows, and the call is free. The blocking-and-billing profile is exactly the information an agent needs and cannot get from annotations.

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?

Two sentences, front-loaded with the core purpose, then the return payloads, then the zero-argument listing mode. Every clause carries distinct information; even the trailing 'Free.' earns its place as a cost signal.

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?

With ten optional parameters and no output schema, the description still tells the agent what comes back (table, coverage, briefing) and how the two operating modes differ. Nothing essential for correct invocation is missing.

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 100%, so the baseline is 3, but the description adds cross-parameter meaning the schema cannot: omitting run_id (and batch_id) switches the tool into listing mode. It also reinforces wait_seconds practice (120–300 for long runs) beyond the schema's per-field description.

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 (status/results of a research run) and ties itself to the producer tool (start_research). It also enumerates the return shapes by run type (table with columns + rows and source links, per-company coverage, cited briefing for Standard/Max), which lets an agent distinguish it from siblings like start_research or cancel_research without opening schemas.

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 clear triggering conditions: call with no run_id to list recent runs, and pass wait_seconds to block on a still-running job. It does not explicitly state when NOT to use it (e.g., prefer get_story for an already-published article, or cancel_research to stop a run), so alternatives are only partially covered.

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