CatchAll (by NewsCatcher)

by com.newscatcherapi.catchall-mcp

initialize_query

Preview suggested validators, enrichments, and date ranges before submitting.

Use when:

You want to inspect/edit auto-generated validators/enrichments before submitting.
You want to preview date adjustments via date_modification_message.

Do not use when:

You want to start processing immediately with final inputs (use submit_query).

Key behavior:

Preview-only endpoint: does not create a job and does not start processing.
Suggestions are LLM-generated and not deterministic across calls.
To reuse suggestions, pass them explicitly to submit_query.

Input Schema

TableJSON Schema

Name	Required	Description
`query`	Yes	Natural language query to preview (required). If you plan to attach a company dataset via `connected_dataset_ids` in the subsequent `submit_query`, do NOT reference the company list here — entity filtering is applied automatically by the dataset, not by the query text.
`api_key`	No	CatchAll API key. Optional if provided via x-api-key header or CATCHALL_API_KEY env var.
`context`	No	Optional guidance on what to prioritize so suggested validators, enrichments, and dates align with your target data points. If a company dataset will be attached in `submit_query`, note that entity-relevance validators (e.g. `company_is_primary_subject`) will be auto-generated — do not ask for them here. Do not mention things like "company list will be attached". Focus on the event or topic only.
`fetch_all_watchlist_news`	No	When `True`, signals that the subsequent job will retrieve all news for connected watchlist entities without topic filtering. Pass this when you intend to use `fetch_all_watchlist_news=True` in `submit_query` so the previewed validators/enrichments are generated accordingly. Requires `connected_dataset_ids` to be set in `submit_query`. Default: `False`.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

TDQS

A4.7/5.0

Behavior5/5

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

No annotations provided, but description fully discloses key behaviors: preview-only, no job creation, LLM-generated non-deterministic suggestions, and instruction to reuse suggestions via 'submit_query'. No contradictions.

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?

Description is well-structured with clear sections (use when, do not use when, key behavior). Front-loaded with core purpose, each sentence adds value without redundancy.

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?

Given full schema coverage, existence of output schema, and the tool's preview nature, description adequately covers necessary context including behavioral traits, usage guidelines, and interaction with 'submit_query'.

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 description coverage is 100%, so baseline is 3. Description adds value by providing usage context for 'query' (not referencing company list) and 'context' (focus on event/topic), going beyond schema descriptions.

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?

Description clearly states 'Preview suggested validators, enrichments, and date ranges before submitting' with specific verb and resource. It distinguishes itself from 'submit_query' by explicitly stating it is preview-only, making purpose unambiguous.

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?

Explicitly lists 'Use when' and 'Do not use when' scenarios with a clear alternative ('submit_query'). However, it does not mention other sibling tools like 'validate_query' that might be related, slightly limiting completeness.

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

All CatchAll (by NewsCatcher) tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.6/5.0

Disambiguation5/5

Each tool is scoped to a specific resource type and action, with clear distinctions between similarly named operations (e.g., pull_results vs pull_job_csv, initialize_query vs validate_query). No two tools appear to perform the same function.

Naming Consistency4/5

Tools consistently use snake_case verb_noun patterns (create_X, get_X, list_X, update_X, delete_X), with domain-specific verbs like submit, pull, initialize, and validate adding semantic clarity. Minor deviations such as pull_* vs get_* and compound names like create_dataset_from_csv are still predictable.

Tool Count2/5

At 60 tools, the server is heavily overstuffed for a single MCP surface. While the broad domain (datasets, entities, jobs, monitors, projects, webhooks) justifies many operations, the sheer volume exceeds typical recommended limits and includes near-duplicates (pull_results vs pull_job_csv, get_dataset vs get_dataset_status), making agent tool selection unwieldy.

Completeness4/5

The tool set provides robust CRUD and lifecycle coverage for all major resources, including special operations like csv import, webhook mapping, and monitor enable/disable. Minor gaps such as the absence of a get_monitor (single monitor details) and no cancel_job can be worked around via list_monitors and waiting for job completion.

Resources

Need Help?