Desearch

List People Found

people-profiles

Read-only

Everyone your own People Searches found on one platform, one entry per person: their best-scoring result (name, handle, url, audience, location, fit score, why they matched, public contacts, and links) and the search that found them (found_by). Free: it reads only people your earlier searches found, runs no new search, and queries no outside source. That data came from public profiles and posts, with only the contacts each person lists publicly. Search by name, handle, bio, or location with q, filter by contact channels (has), audience, fit score, location, or verification, and sort by score, recent, or audience. People from searches that ended more than 30 days ago are left out.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "platform": "<platform>"
    },
    "name": "people-profiles"
  }
}

Input Schema

Name	Required	Description
`q`	No	Text in the name, handle, bio, or location, example: 'skincare'.
`has`	No	Channels every person must have, example: ['email', 'instagram']. 'email' is a public email; the others are a link of that type.
`sort`	No	'score' (API default), 'recent', or 'audience'.
`limit`	No	People per page (1-200, default 25).
`cursor`	No	next_cursor from the previous page.
`location`	No	Text in the location, example: 'united states'.
`platform`	Yes	Platform: 'x', 'youtube', 'linkedin', or 'tiktok'.
`verified`	No	Only verified accounts. Only X and TikTok people carry a verified flag.
`min_score`	No	Minimum fit score (0-100).
`max_audience`	No	Maximum followers (subscribers on YouTube).
`min_audience`	No	Minimum followers (subscribers on YouTube).

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 19, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Annotations only say read-only/non-destructive; the description adds much more: no new search is executed, no outside source is queried, provenance is public profiles and posts with only publicly listed contacts, results are deduplicated to one entry per person using the best-scoring result, and searches older than 30 days are excluded. These are exactly the operational facts an agent needs before deciding whether the call is free, safe, and complete.

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?

Purpose and dedupe semantics are front-loaded, and every later clause (returned fields, no-new-search, filter list, 30-day cutoff) carries information the schema does not, which matters given there is no output schema. The opening sentence is an overlong run-on with a parenthetical field list that taxes readability, costing a point.

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 must describe return contents and it does (name, handle, url, audience, location, fit score, match rationale, public contacts, links, found_by). For an 11-parameter read tool, the combination of provenance, retention window, dedupe rule, and the full filter/sort enumeration leaves nothing an agent needs missing.

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?

With 100% schema description coverage, the schema already documents every parameter, including enums and the default sort. The description's "search by q, filter by has/audience/fit score/location/verification, sort by score/recent/audience" is a faithful restatement that adds no syntax, units, or combination rules beyond the schema, so baseline 3 applies.

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?

"Everyone your own People Searches found on one platform, one entry per person" states the resource, the scope (your own prior searches), and the result shape (deduped per person with best-scoring result). Combined with "runs no new search," an agent can immediately tell this apart from people-search, which originates searches rather than reading their output.

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?

"Free: it reads only people your earlier searches found, runs no new search" tells the agent when this is the cheap read path, and the 30-day retention clause sets a hard boundary on what is retrievable. It never names people-search as the alternative to use when new discovery is needed, leaving that routing inference to the agent.

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

All Desearch tools Inspect

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.