Skip to main content
Glama
Sign In
Rolli MCP

Rolli MCP

by rolliinc
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

user_search

Search social media profiles by username or URL across Twitter, Facebook, or Instagram, then poll until results are complete and return full posts with date filters.

Instructions

Create a user profile search on a social media platform. Polls until the search is complete and returns the full results. Oversized responses are truncated (truncated: true) — read the complete post list in pages with get_user_search_posts (offset, limit, fields=lean). A status of results_pending means the search succeeded but results are still being written; fetch them with get_user_search.

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": {
      "query": "<query>",
      "platform": "<platform>"
    },
    "name": "user_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryYesUsername or profile URL to search
end_dateNoEnd date (YYYY-MM-DD)
platformYesPlatform to search
start_dateNoStart date (YYYY-MM-DD)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.5.0
    • removedInput schema / additionalProperties
      Removed value: -false
  2. First observedv1.1.7

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses that the call polls until completion (latency/blocking behavior), that responses may be truncated with a 'truncated: true' marker, and that 'results_pending' is a success state rather than a failure. It omits permission/auth requirements and whether the created search persists or is billed, which keeps it below a 5.

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?

Four sentences, front-loaded with the core action, then the polling/truncation/pending behaviors in priority order. Dense and mostly waste-free, though the truncation and pending sentences could be tightened into one.

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?

No output schema exists, so the description must explain returns; it covers the truncated flag, the results_pending status, and the pagination path, which is what an agent needs to act on results. It stops short of describing the post object shape or the full result payload, a minor gap for a 4-parameter search tool.

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 the schema already documents query, platform, and the date bounds; the description adds no extra meaning about start_date/end_date semantics or platform-specific behavior. Baseline 3 applies, with the only added hint (fields=lean) referring to a sibling tool rather than this tool's parameters.

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 ('Create a user profile search on a social media platform') and implicitly scopes it against sibling search tools (keyword_search, expert_search) by naming the user-search follow-up tools. An agent can identify this as the user-scoped search entry point without opening the 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 conditional routing: paginate with get_user_search_posts when truncated, and fetch with get_user_search when status is results_pending. It does not explicitly say when to choose this over keyword_search or expert_search, so the sibling-selection guidance is incomplete.

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

Deploy Server

Other Tools