Skip to main content
Glama

dialogbrain

by io.github.saloprj
OverviewDiscussionsAdmin

linkedin_search

Read-onlyIdempotent

Search LinkedIn for people (other categories are not available yet). Returns name, headline, location, connection degree, profile URL and member_urn (what linkedin.invite takes), up to 50 per page; pass the answer's next_page as cursor for more. Put a role, company or place in keywords (e.g. 'procurement manager Bangkok'); location and industry take LinkedIn's numeric ids only, network_distance F/S/O, role filters by title.

Input Schema

NameRequiredDescriptionDefault
apiNoLinkedIn product to search withclassic
roleNoRole/title filter
limitNoPeople per page (at most 50)
cursorNonext_page from the previous answer, for the next page
categoryNoWhat to search forpeople
industryNoIndustry filter IDs
keywordsNoSearch keywords
locationNoLinkedIn geo ids (numbers, e.g. 105146118 for Thailand); a place name belongs in keywords
in_workspaceNoRun this one call in this workspace id instead of the session's. Nothing is stored; other sessions are not affected.
from_account_idNoWhich of the workspace's LinkedIn accounts to act as (its id from channels.list). Connections, invitations and search results are that person's own network. OMIT to use the default LinkedIn account (in a LinkedIn conversation, the account that conversation belongs to); pass it whenever the workspace has more than one. An account this workspace cannot use is refused, never swapped for another.
network_distanceNoConnection degree: F=1st, S=2nd, O=3rd+

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • addedInput schema / properties / cursor
      Added value: +{
+  "description": "next_page from the previous answer, for the next page",
+  "type": "string"
+}
    • removedInput schema / properties / has_job_offers
      Removed value: -{
-  "description": "Filter for people with job offers",
-  "type": "boolean"
-}
    • changedInput schema / properties / limit / description
      Previous value: -"Maximum results to return"New value: +"People per page (at most 50)"
    • changedInput schema / properties / limit / maximum
      Previous value: -100New value: +50
    • changedInput schema / properties / location / description
      Previous value: -"Location filter IDs (use linkedin.search_filters to resolve)"New value: +"LinkedIn geo ids (numbers, e.g. 105146118 for Thailand); a place name belongs in keywords"
    • removedInput schema / properties / url
      Removed value: -{
-  "description": "Direct LinkedIn search URL (alternative to keyword/filter search)",
-  "type": "string"
-}
  2. Added
  3. Removed
  4. Added
  5. Removed
  6. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already cover read-only/idempotent/non-destructive, and the description adds details they cannot: the exact return fields, a 50-per-page cap, and that `next_page` from the answer feeds `cursor`. It stops short of explaining what the three `api` products (classic / sales_navigator / recruiter) change about results or quota, which is the one behavioral unknown left.

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

Conciseness4/5

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

One dense paragraph that front-loads scope, then returns, then pagination, then query syntax — a sensible order with no filler. It is packed tightly enough that the parameter guidance reads as a run-on list rather than discreet sentences, which costs a little clarity.

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 no output schema, the description correctly spends words enumerating the returned fields (name, headline, location, degree, URL, member_urn) and explains pagination, which is exactly what an agent needs to chain into `linkedin_invite`. The remaining hole is the `api` selector and any rate-limit behavior.

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?

Coverage is 100%, so the schema carries the baseline, yet the description still adds meaning: `location`/`industry` take LinkedIn numeric ids only (with the schema's Thailand example reinforced), `network_distance` is F=1st/S=2nd/O=3rd+, and `cursor` is explicitly the previous answer's `next_page`. The `api` parameter is listed in the schema but never explained in the description.

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?

States a specific verb and resource ("Search LinkedIn for people") and immediately narrows scope with "other categories are not available yet", which preempts the misleading `category` enum. It also names the downstream consumer of `member_urn` (linkedin.invite), so an agent can place the tool in a workflow without opening another schema.

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?

Gives concrete query-construction guidance: put a role, company or place in `keywords` with an example ("procurement manager Bangkok"), and use `role` for title filtering. It does not state when to prefer this over `linkedin_search_filters`, `contacts_find` or `channels_contacts`, so the alternative-selection gap is real but the in-tool guidance is strong.

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

All dialogbrain toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources