Skip to main content
Glama

Search people

people_search
Read-onlyIdempotent

Search people

Searches people on each platform as one of the team's account links, like the platform's own search box.

Needs the Advanced API add-on, and directory:typeahead on each account link. Each search is a call to the platform as the account link, and each account link can make 20 per minute, 300 per hour and 1500 per day, so the platform doesn't flag its session; past a limit, it is listed in failures with platformRateLimited.

Use the result's target to reach that person on endpoints like Send message or Send connection request.

Input Schema

NameRequiredDescriptionDefault
qYesA name or username, as typed into the platform's own people search.
reachNo`contacts`, the default, searches people each account already messages. `network` also searches beyond them, where the platform separates the two.
enrichNo`true` fetches and stores every result Inboxapp hasn't stored yet, so each comes back as a full profile. A result that can't be fetched or stored is left out. Slower. Defaults to `false`.
platformNoSearches these platforms. Defaults to every available platform. With `accountLinkId`, keeps only the account links on these platforms. Repeat the key to match any of several.
accountLinkIdNoSearches from these account links. Each platform is searched once, from the oldest account link given on it; IDs that match no account link are ignored. Without it, each platform is searched from its oldest active account link that can search. Repeat the key to match any of several.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / $defs / Platform / description
      Previous value: -"The platform. Every team can use twitter, linkedin; a team may have others enabled."New value: +"The platform. Every team can use twitter, linkedin, whatsapp; a team may have others enabled."
    • changedInput schema / $defs / Platform / examples
      Previous value: -[
      -  "twitter",
      -  "linkedin"
      -]New value: +[
      +  "twitter",
      +  "linkedin",
      +  "whatsapp"
      +]
  2. Added

TDQS

A4.1/5.0
Behavior5/5

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

Beyond the readOnly/openWorld/idempotent annotations, it discloses concrete rate limits per account link (20/min, 300/hr, 1500/day), the reason for them (avoiding platform session flags), and the exact failure surface (`failures` entries tagged `platformRateLimited`). That is the kind of operational context an agent cannot derive from the annotations or schema.

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?

It is front-loaded (purpose, then prerequisites, then limits, then follow-up) and each sentence carries information. The only waste is the opening line 'Search people', which merely restates the title before the real definition begins.

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?

With no output schema, the description compensates by naming the returned `target` field and the `failures` array with its `platformRateLimited` reason, plus prerequisites and quota exhaustion behavior. For an open-world, multi-account search tool, an agent has everything needed to call it and interpret partial failures.

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%, and each parameter (q, reach, enrich, platform, accountLinkId) is already well documented in the schema, including defaults and multi-value behavior. The description adds only indirect color — that searches run per account link and are rate-limited — but no per-parameter meaning beyond the schema, so the baseline 3 applies.

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 first sentence states a specific verb and resource ('Searches people on each platform') and adds the analogy to the platform's own search box, so the operation is unambiguous. It stops short of naming the nearest sibling (contacts_list) to contrast directory search from stored contacts, so it is clear but not fully sibling-differentiated.

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?

It states prerequisites (Advanced API add-on and the `directory:typeahead` scope on each account link) and closes with a downstream routing hint: use the result's `target` with Send message or Send connection request. What is missing is an explicit 'when not to use this' — e.g. versus contacts_list when the person is already a stored contact.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources