Skip to main content
Glama
Crawlora-org

Crawlora MCP

Official

datasets_journalists_search

Search public journalist and reporter records by outlet, beat, or role to find PR outreach contacts with contact info and readiness signals.

Instructions

Search the journalists dataset. Searches the journalists index (dataset id enum value journalists) — public journalist and reporter records crawled from news outlets' own staff/author pages, for PR outreach. Each record carries the outlet, title, best-effort beat topics, and any public contact info found on that outlet's own page, plus deterministic record_type, role_type, email_kind, and outreach-readiness quality signals. There is no cross-outlet upstream search; this dataset is built by crawling a curated roster of outlets ourselves. vertical enum: tech, crypto, marketing, consumer_tech, consumer_policy, cybersecurity, health, gaming, climate, business, entertainment, sports, legal, science, politics, real_estate, automotive, travel, food, education, design, film_tv, fashion, music, personal_finance, tech_independent, culture_independent, local_news, construction, banking, retail, aerospace_defense, energy, agriculture, local_business. contact_type enum: email, social, none. record_type enum: person, desk, organization, syndicated_byline, unknown. role_type enum: staff, editor, reporter, contributor, freelancer, columnist, non_editorial, unknown. email_kind enum: individual_work, individual_personal_public, shared_desk, tips_or_submissions, outlet_generic, unknown. sort enum: relevance, name_asc, outlet_asc, crawled_desc, readiness_desc.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
qNoFull-text match on the journalist's name, title, and bio, max 256 characters
pageNoPage number, defaults to 1
sortNoSort enum: relevance, name_asc, outlet_asc, crawled_desc, readiness_desc
topicNoExact topic filter, e.g. security, stablecoins. Use the values returned by facets?facet=topic
outletNoExact outlet id filter, e.g. techcrunch, coindesk. Use the ids returned by facets?facet=outlet
verticalNoExact beat-vertical filter. Enum: tech, crypto, marketing, consumer_tech, consumer_policy, cybersecurity, health, gaming, climate, business, entertainment, sports, legal, science, politics, real_estate, automotive, travel, food, education, design, film_tv, fashion, music, personal_finance, tech_independent, culture_independent, local_news, construction, banking, retail, aerospace_defense, energy, agriculture, local_business, general_news
page_sizeNoPage size, defaults to 20 and maxes at 100; page * page_size must be <= 10000
role_typeNoRole classification filter. Enum: staff, editor, reporter, contributor, freelancer, columnist, non_editorial, unknown
email_kindNoEmail semantics filter. Enum: individual_work, individual_personal_public, shared_desk, tips_or_submissions, outlet_generic, unknown
record_typeNoRecord classification filter. Enum: person, desk, organization, syndicated_byline, unknown
contact_typeNoContact-availability filter. Enum: email, social, none
min_outreach_readinessNoMinimum outreach-readiness score, from 0 to 100

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.17.6
    • changedInput schema / properties / vertical / enum
      Previous value: -[
      -  "tech",
      -  "crypto",
      -  "marketing",
      -  "consumer_tech",
      -  "consumer_policy",
      -  "cybersecurity",
      -  "health",
      -  "gaming",
      -  "climate",
      -  "business",
      -  "entertainment",
      -  "sports",
      -  "legal",
      -  "science",
      -  "politics",
      -  "real_estate",
      -  "automotive",
      -  "travel",
      -  "food",
      -  "education",
      -  "design",
      -  "film_tv",
      -  "fashion",
      -  "music",
      -  "personal_finance",
      -  "tech_independent",
      -  "culture_independent",
      -  "local_news",
      -  "construction",
      -  "banking",
      -  "retail",
      -  "aerospace_defense",
      -  "energy",
      -  "agriculture",
      -  "local_business"
      -]New value: +[
      +  "tech",
      +  "crypto",
      +  "marketing",
      +  "consumer_tech",
      +  "consumer_policy",
      +  "cybersecurity",
      +  "health",
      +  "gaming",
      +  "climate",
      +  "business",
      +  "entertainment",
      +  "sports",
      +  "legal",
      +  "science",
      +  "politics",
      +  "real_estate",
      +  "automotive",
      +  "travel",
      +  "food",
      +  "education",
      +  "design",
      +  "film_tv",
      +  "fashion",
      +  "music",
      +  "personal_finance",
      +  "tech_independent",
      +  "culture_independent",
      +  "local_news",
      +  "construction",
      +  "banking",
      +  "retail",
      +  "aerospace_defense",
      +  "energy",
      +  "agriculture",
      +  "local_business",
      +  "general_news"
      +]
  2. Changed9 schema fields changedv1.17.5
    • addedInput schema / properties / contact_type / enum
      Added value: +[
      +  "email",
      +  "social",
      +  "none"
      +]
    • addedInput schema / properties / email_kind
      Added value: +{
      +  "description": "Email semantics filter. Enum: individual_work, individual_personal_public, shared_desk, tips_or_submissions, outlet_generic, unknown",
      +  "enum": [
      +    "individual_work",
      +    "individual_personal_public",
      +    "shared_desk",
      +    "tips_or_submissions",
      +    "outlet_generic",
      +    "unknown"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / min_outreach_readiness
      Added value: +{
      +  "description": "Minimum outreach-readiness score, from 0 to 100",
      +  "type": "integer"
      +}
    • addedInput schema / properties / record_type
      Added value: +{
      +  "description": "Record classification filter. Enum: person, desk, organization, syndicated_byline, unknown",
      +  "enum": [
      +    "person",
      +    "desk",
      +    "organization",
      +    "syndicated_byline",
      +    "unknown"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / role_type
      Added value: +{
      +  "description": "Role classification filter. Enum: staff, editor, reporter, contributor, freelancer, columnist, non_editorial, unknown",
      +  "enum": [
      +    "staff",
      +    "editor",
      +    "reporter",
      +    "contributor",
      +    "freelancer",
      +    "columnist",
      +    "non_editorial",
      +    "unknown"
      +  ],
      +  "type": "string"
      +}
    • changedInput schema / properties / sort / description
      Previous value: -"Sort enum: relevance, name_asc, outlet_asc, crawled_desc"New value: +"Sort enum: relevance, name_asc, outlet_asc, crawled_desc, readiness_desc"
    • addedInput schema / properties / sort / enum
      Added value: +[
      +  "relevance",
      +  "name_asc",
      +  "outlet_asc",
      +  "crawled_desc",
      +  "readiness_desc"
      +]
    • changedInput schema / properties / vertical / description
      Previous value: -"Exact beat-vertical filter. Enum: tech, crypto, marketing, consumer_tech, consumer_policy, cybersecurity, health, gaming, climate, business, entertainment, sports, legal, science, politics, real_estate, automotive, travel, food, education, design, film_tv, fashion, music, personal_finance, tech_independent, culture_independent, local_news, construction, banking, retail, aerospace_defense, energy, agriculture, local_business"New value: +"Exact beat-vertical filter. Enum: tech, crypto, marketing, consumer_tech, consumer_policy, cybersecurity, health, gaming, climate, business, entertainment, sports, legal, science, politics, real_estate, automotive, travel, food, education, design, film_tv, fashion, music, personal_finance, tech_independent, culture_independent, local_news, construction, banking, retail, aerospace_defense, energy, agriculture, local_business, general_news"
    • addedInput schema / properties / vertical / enum
      Added value: +[
      +  "tech",
      +  "crypto",
      +  "marketing",
      +  "consumer_tech",
      +  "consumer_policy",
      +  "cybersecurity",
      +  "health",
      +  "gaming",
      +  "climate",
      +  "business",
      +  "entertainment",
      +  "sports",
      +  "legal",
      +  "science",
      +  "politics",
      +  "real_estate",
      +  "automotive",
      +  "travel",
      +  "food",
      +  "education",
      +  "design",
      +  "film_tv",
      +  "fashion",
      +  "music",
      +  "personal_finance",
      +  "tech_independent",
      +  "culture_independent",
      +  "local_news",
      +  "construction",
      +  "banking",
      +  "retail",
      +  "aerospace_defense",
      +  "energy",
      +  "agriculture",
      +  "local_business"
      +]
  3. Changed1 schema field changedv1.6.0
    • changedInput schema / properties / vertical / description
      Previous value: -"Exact beat-vertical filter. Enum: tech, crypto, marketing, consumer_tech, consumer_policy, cybersecurity, health, gaming, climate, tech_independent, culture_independent"New value: +"Exact beat-vertical filter. Enum: tech, crypto, marketing, consumer_tech, consumer_policy, cybersecurity, health, gaming, climate, business, entertainment, sports, legal, science, politics, real_estate, automotive, travel, food, education, design, film_tv, fashion, music, personal_finance, tech_independent, culture_independent, local_news, construction, banking, retail, aerospace_defense, energy, agriculture, local_business"
  4. Addedv1.5.0

TDQS

A3.6/5.0
Behavior4/5

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

No annotations are provided, so the description carries the full burden, and it does substantial work: it discloses the data provenance (self-crawled curated roster, no upstream cross-outlet search), that beat topics are 'best-effort', and that role/email/readiness fields are 'deterministic quality signals'. This tells the agent to treat some fields as authoritative and others as noisy. It stops short of covering pagination/result-window behavior, but the schema handles that.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The opening is well front-loaded: it leads with the action, the corpus, and the provenance caveat. However, the back half is largely verbatim enum dumps (vertical, contact_type, record_type, role_type, email_kind, sort) that are already fully enumerated in the schema, spending significant length on redundant content.

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 12 parameters, no required fields, and no output schema, the description needs to convey both filter semantics and what results look like. It describes the record shape (outlet, title, beat topics, contact info, quality signals) well and explains the dataset's construction, leaving only minor gaps around pagination windows and how filters combine.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

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 mainly re-lists the six enum value sets verbatim, which duplicates the schema rather than adding syntax, format, or defaulting guidance beyond it. No additional semantic value is contributed over the structured fields.

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?

The description states a specific verb and resource ('Search the journalists dataset') and explains what the dataset contains (public journalist/reporter records crawled from outlet staff/author pages, for PR outreach). It gives the agent a clear mental model of the corpus, though it never explicitly names its closest siblings (datasets_journalists_facets / datasets_journalists_item) to distinguish itself from them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: 'for PR outreach' signals the intended use case, and the note about 'no cross-outlet upstream search' clarifies data boundaries. But it never states when to reach for this tool over datasets_journalists_facets (to enumerate filter values) or datasets_journalists_item (to fetch one record), so the routing decision is left to inference.

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

Deploy Server

Other Tools