Rolli MCP

get_user_search_posts

Retrieve raw posts from a user search and page through results with offset and limit; use lean fields to fit more text-focused posts per response.

Instructions

Get raw posts from a user search. The first line says how many of the profile's posts this response shows and the offset of the next page; total, returned and offset are in the JSON. Read a large search in pages with offset and limit, and fields=lean when the text matters more than media and profile URLs. A response over the size cap is marked truncated: true.

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": {
      "search_id": "<search_id>"
    },
    "name": "get_user_search_posts"
  }
}

Input Schema

Name	Required	Description
`limit`	No	Posts per page, 1 to 1000 (default: every remaining post)
`fields`	No	lean leaves out media_url, profile_url and sentiment_reason, so roughly twice as many posts fit in one response (default: full)
`offset`	No	Posts to skip (default 0). To read the next page, use the offset the previous response's first line gives.
`search_id`	Yes	User search ID

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedv1.5.0Nov 4, 2026

removedInput schema / additionalProperties
```
Removed value: -false
```

addedInput schema / properties / fields

Added value: +{
+  "description": "lean leaves out media_url, profile_url and sentiment_reason, so roughly twice as many posts fit in one response (default: full)",
+  "enum": [
+    "full",
+    "lean"
+  ],
+  "type": "string"
+}

addedInput schema / properties / limit

Added value: +{
+  "description": "Posts per page, 1 to 1000 (default: every remaining post)",
+  "maximum": 1000,
+  "minimum": 1,
+  "type": "integer"
+}

addedInput schema / properties / offset

Added value: +{
+  "description": "Posts to skip (default 0). To read the next page, use the offset the previous response's first line gives.",
+  "maximum": 9007199254740991,
+  "minimum": 0,
+  "type": "integer"
+}

addedInput schema / properties / search_id / maximum
```
Added value: +9007199254740991
```

First observedv1.1.7Mar 18, 2026

TDQS

A3.9/5.0

Behavior4/5

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

With no annotations, the description carries the full disclosure burden and does well: it explains the response's first line, the JSON fields (total, returned, offset), the truncation flag for oversized responses, and the payload tradeoff of lean mode. It omits failure modes (invalid search_id, expired searches) and any permission or rate-limit context, which keeps it short of 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?

Three tight sentences, front-loaded with the purpose before the response-shape and pagination details. Every sentence carries information, though the response-format sentence is dense and slightly awkward to parse on a first read.

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?

There is no output schema, so the description must explain return values, and it does: the first line's counts, the total/returned/offset fields, and the truncated marker. It never says where a valid search_id comes from (presumably user_search / get_user_search) or what happens on an invalid ID, leaving a small gap for a read tool with no annotations.

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 coverage is 100%, so all four parameters are already documented, including the lean enum's omitted fields and the offset-as-next-page hint. The description mostly restates that contract plus a usage rationale for lean, adding modest meaning beyond the schema rather than new syntax or constraints.

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?

"Get raw posts from a user search" gives a concrete verb (get), resource (posts), and scope (from a user search), which separates it from the metadata-oriented get_user_search and from get_keyword_search_posts. It never explicitly names those siblings, so the differentiation rests on the name and implication rather than on stated contrast.

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 description says when to paginate a large search with offset and limit, and when to pick fields=lean ("when the text matters more than media and profile URLs"). It supplies a concrete next-page procedure (reuse the offset from the previous response's first line) but gives no guidance on when to call this versus get_user_search or get_keyword_search_posts.

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