Skip to main content
Glama

ZOOQ - LinkedIn Data for AI Agents

by io.github.baldiga

companies_employees_data

Read-onlyIdempotent

People who work or worked at an organization (professional records, same shape as /search/people). Cursor-paginated. (Costs 10 Zooq credits.)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
slugYesCompany public slug — the part after linkedin.com/company/. Resolve via companies_name_lookup (or /search/companies) if you only have a name — read data[].slug.
sortNoOrdering. Accepted values: newest, oldest, recently_left (use recently_left with current_only=false).
limitNoResults per page, 1-50 (default 20).
titleNoPartial job-title filter (min 3 chars), e.g. software engineer. Combine with current_only=true to target a current role.
cursorNoOpaque pagination cursor from the previous response.
geo_cityNoCity filter (min 3 chars).
start_yearNoMatch people who started in this year (1900-current).
start_monthNoMatch people who started in this month (1-12), paired with start_year.
current_onlyNoRestrict to people in a current role at the company.
geo_country_codeNoISO country code filter, e.g. us.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
itemsNoArray in the example

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent, open-world, and non-destructive behavior. The description adds useful non-obvious context: cursor pagination, a 10-credit cost, inclusion of current and former employees, and output shape compatibility with /search/people. No contradiction with annotations 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 three tight clauses with no filler: scope, output/behavior, and cost. It front-loads the core purpose and each phrase earns its place.

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?

Given the rich output schema and annotations, the description covers the essential non-schema context: pagination behavior, credit cost, and the population of people returned. The only notable gap is explicit guidance on when to use this versus sibling tools, but that is largely a usage-guideline concern.

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 every parameter is already documented in the input schema. The tool description itself does not add parameter-level detail, so the baseline 3 is appropriate.

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 clearly identifies the resource: people who currently work or previously worked at an organization, and notes output shape parity with '/search/people'. It does not include an explicit verb like 'list' or 'retrieve', and it does not explicitly contrast with siblings such as search_people, so it falls just short of a 5.

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?

The intended context is implied: use this tool to get employees of an organization identified by company slug. However, the description does not explicitly say when to choose this over alternatives like search_people or profile_employment_history, and it provides no exclusions or routing conditions.

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 toolsInspect
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.

Resources