Time Machine News

Search newspaper pages

search_newspapers

Read-onlyIdempotent

Search full text of historical US newspapers from 1700s–1963. Filter by date, state, or newspaper to get matching pages, snippets, and page links.

Instructions

Search the full text of historical US newspaper pages (1700s-1963).

Returns matching pages with the newspaper, date, place, a text snippet around the
match, and a page_url to pass to get_page_text. Add a date range and a state or
newspaper whenever possible; broad searches are slow.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`page`	No	Results page number.
`match`	No	'all' words (default), 'any' word, or the exact 'phrase'.	all
`query`	Yes	Words to find in the text of newspaper pages.
`state`	No	US state or territory where the paper was published, e.g. 'Kansas' or 'KS'.
`end_date`	No	Latest publication date: YYYY, YYYY-MM, or YYYY-MM-DD.
`per_page`	No	Results per page.
`start_date`	No	Earliest publication date: YYYY, YYYY-MM, or YYYY-MM-DD.
`newspaper_lccn`	No	Limit to one newspaper by its LCCN, e.g. 'sn83030214' (from find_newspapers).
`front_pages_only`	No	Only search front pages.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 3, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already declare readOnly, openWorld and idempotent, so safety is covered. The description adds real behavioral context beyond that: broad searches are slow (performance/latency warning) and the result shape includes a page_url intended for get_page_text chaining.

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 short paragraphs, front-loaded with what the tool does and followed by the result shape and the efficiency caveat. No sentence is filler.

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?

With an output schema present, the description need not explain return fields, yet it still summarizes them usefully. Parameters are fully documented in the schema. Minor gaps remain (page/per_page limits, no explicit next-step for pagination), but nothing needed to invoke the tool 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 description coverage is 100%, so the baseline is 3. The description goes slightly beyond it by recommending which filters (date range, state/newspaper) actually make searches fast, giving practical meaning to start_date, end_date, state and newspaper_lccn rather than restating them.

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?

States a specific verb (Search) plus resource (full text of historical US newspaper pages) and even bounds the corpus (1700s-1963). It hints at the workflow handoff to get_page_text, but never contrasts itself with find_newspapers or front_pages_on_date, so sibling differentiation is only partial.

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?

'Add a date range and a state or newspaper whenever possible; broad searches are slow' gives clear when-to-narrow guidance and a performance rationale. It stops short of explicit exclusions or naming when a sibling (e.g. find_newspapers to resolve an LCCN) should be used instead.

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

Deploy Server