Skip to main content
Glama
Sign In

Desearch

by io.github.Desearch-ai
OverviewDiscussionsAdmin

Export People Found

people-search-export
Read-only

The people your own People Searches found, as CSV or JSON Lines text: one search (task_id), or everyone found on one platform (platform, with the same q, sort, and filters as people-profiles). Free: it reads people your earlier searches found and runs no new search. The reply is a note with the row count, then the file text cut at a row boundary to max_rows rows and 50,000 characters; the note says how many rows were cut and where to get the whole file. CSV keeps its header row. The data came from public profiles and posts, with only the contacts each person lists publicly.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "people-search-export"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoPlatform export only: text in the name, handle, bio, or location.
hasNoChannels every person must have, example: ['email']. 'email' is a public email; the others are a link of that type.
sortNoPlatform export only: 'score' (API default), 'recent', or 'audience'.
formatNo'csv' (default) or 'jsonl' (one JSON object per line).csv
task_idNoExport one search: the task_id returned by people-search. Omit it and set platform to export everyone your searches found on that platform.
locationNoText in the location, example: 'united states'.
max_rowsNoMost rows to return (1-1000, default 100). The reply also stops before 50,000 characters of file text.
platformNoWithout task_id: export everyone found on 'x', 'youtube', 'linkedin', or 'tiktok'.
verifiedNoOnly verified accounts. Only X and TikTok people carry a verified flag.
min_scoreNoMinimum fit score (0-100).
max_audienceNoMaximum followers (subscribers on YouTube).
min_audienceNoMinimum followers (subscribers on YouTube).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.5/5.0
Behavior5/5

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

Goes well beyond the readOnly/openWorld annotations: it discloses that the reply is a note with a row count followed by file text, that output is truncated at max_rows and 50,000 characters at a row boundary, that the note reports how much was cut and where to get the full file, and that CSV retains its header. That truncation behavior is critical and not derivable from the 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?

The core scoping (what it exports, that it's free, and the truncation behavior) is front-loaded and no sentence is filler. It is a dense single block, though, and the provenance sentence at the end is arguably secondary to the truncation note.

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?

For a 12-parameter, read-only tool with no output schema, the description covers the export modes, the return shape, truncation limits, and data provenance, which is enough to call it correctly. The filter parameters are left entirely to the schema, which is acceptable at 100% coverage, but it stops just short of fully complete.

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?

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning: it frames task_id vs. platform as mutually exclusive modes and notes that platform-mode filters mirror people-profiles. It explains the parameters' relationships rather than repeating their definitions.

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: export the people your own People Searches found, as CSV or JSON Lines. It also distinguishes the two export modes (one task_id vs. one platform) and, via the 'runs no new search' line, implicitly separates itself from people-search and people-profiles.

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?

The 'Free: it reads people your earlier searches found and runs no new search' line gives a clear usage condition, and the task_id/platform distinction tells the agent which mode to pick. It never names a sibling alternative explicitly (e.g. 'use people-search if you have no results yet'), so it falls short of a 5.

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

All Desearch 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