ZOOQ - LinkedIn Data for AI Agents

search_people_live

Read-onlyIdempotent

LIVE people search — the only endpoint that filters by current company, past company AND school together. Complements search_people (the deduplicated dataset, cursor-paginated, plain-string geo): use this one for company-history sourcing, that one for broad firmographic filtering. Offset-paginated. Not-found is free upstream. (Costs 10 Zooq credits.)

Input Schema

TableJSON Schema

Name	Required	Description
`count`	No	Results per page, 0-50 (default 20).
`start`	No	Pagination offset, 0-999.
`title`	No	Job-title free-text filter.
`school`	No	Institution id(s), comma-separated. NOTE: this is the LIVE id namespace; the inst_ ids from g_institution_lookup are the dataset namespace and are not known to be interchangeable — unverified, treat with care.
`keyword`	No	Free-text keyword across the profile.
`industry`	No	Industry id(s), comma-separated. Takes an upstream id, NOT free text. No Zooq or upstream endpoint currently mints these ids, so free text is ignored (you get unfiltered results) — leave it unset until that changes. See ROADMAP F.
`lastName`	No	Last-name filter.
`firstName`	No	First-name filter.
`geoEntityId`	No	Geo entity id — this is LinkedIn's own public geo id, and it works. To find one: type your target city, state or country into the location box on LinkedIn search, pick the right match from the auto-complete dropdown, press enter to load the results page, then read `geoId=` followed by a long number out of the browser address bar (e.g. Israel = 101620260). Comma-separate for several. Resolve once and reuse it. Verified working on this endpoint. If you would rather filter by plain text, search_people takes geo_city / geo_country_code instead.
`pastCompany`	No	Numeric organization id(s), comma-separated — alumni sourcing: people who USED to work there. Same id source as currentCompany. This filter has no equivalent on search_people.
`currentCompany`	No	Numeric organization id(s), comma-separated — people who work there NOW. Mint the id with companies_entity_id (slug -> id), then reuse it.
`profileLanguage`	No	Profile primary language code, e.g. en.
`serviceCategory`	No	Service-category filter (for profiles offering services).

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

TDQS

A4.7/5.0

Behavior5/5

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

Annotations already establish read-only, non-destructive, idempotent behavior. The description adds genuinely useful behavioral context beyond that: it is LIVE data, offset-paginated, has no charge for not-found results, and costs 10 credits per call. No contradiction exists.

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?

The description is compact, front-loads the core differentiator, and each sentence contributes either differentiation, usage guidance, or operational detail. There is no filler or 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 rich annotations, full parameter descriptions, and an output schema, the description supplies the remaining operational context an agent needs: pagination style, cost, not-found behavior, and how this tool complements search_people. Nothing critical is missing for correct invocation.

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 of 3 applies. The tool description itself does not add parameter-level detail, but the schema already carries comprehensive guidance, including caveats about id namespaces and free-text limitations.

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?

Names a specific verb and resource ('LIVE people search') and immediately states its unique capability: filtering by current company, past company, and school together. It also distinguishes itself from search_people, making it clearly identifiable among the sibling tools 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 Guidelines5/5

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

Explicitly tells the agent when to choose this tool over the main alternative: 'use this one for company-history sourcing, that one for broad firmographic filtering.' The contrast in pagination style (offset-paginated vs. cursor-paginated) and geo handling further clarifies selection.

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

All ZOOQ - LinkedIn Data for AI Agents 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

A3.7/5.0

Disambiguation3/5

Most tools are separated by domain prefixes and the descriptions are unusually explicit about differences, but there are direct overlaps: companies_name_lookup is the same upstream as search_companies, companies_entity_id vs companies_universal_name_to_id resolve different id spaces, and search_people/search_people_live plus search_companies/search_companies_live cover similar ground. An agent can usually pick correctly, but only after close reading.

Naming Consistency4/5

The set is consistently snake_case with readable domain prefixes like companies_, jobs_, posts_, profile_, and search_. Deviations include the unexplained g_* prefix, jobs_details_v2's version suffix, affiliate_program lacking a resource prefix, and the duplicate naming convention of companies_name_lookup vs search_companies.

Tool Count2/5

45 tools is well above the 25+ threshold and creates a heavy surface for an agent to scan. While the domains are broad, some tools are redundant (companies_name_lookup/search_companies) or tangential (affiliate_program), so the count is not fully justified.

Completeness4/5

The server covers people, companies, jobs, posts, email, schools, and skills with both search and detail endpoints, which is strong for a read-only LinkedIn API. Obvious gaps like a global post search or a company followers list are absent, but the existing paths support most workflows without dead ends.

search_people_live

Input Schema

Output Schema

TDQS

Glama MCP Gateway

TDQS

Resources