Rolli MCP

expert_search

Find experts matching a natural-language query using an AI recommendation engine; polls until complete and returns full expert profiles with contact info and match summaries.

Instructions

Find experts matching a natural-language query using Rolli's AI-driven recommendation engine. Polls until the search is complete and returns the full list of recommended experts (name, professional title, location, contact info, expertise keywords, and an AI-generated summary explaining why each expert matches). A status of results_pending means the search succeeded but results are still being written; fetch them with get_expert_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>"
    },
    "name": "expert_search"
  }
}

Input Schema

Name	Required	Description	Default
`query`	Yes	Natural-language description of the topic, expertise area, or expert profile to find (e.g. "AI ethics researchers", "climate scientists who can speak on tipping points")

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv1.5.0Nov 4, 2026
- removedInput schema / additionalProperties
```
Removed value: -false
```
Addedv1.3.0Jun 3, 2026

TDQS

A4.2/5.0

Behavior4/5

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

With no annotations supplied the description carries the full burden, and it does disclose real behavior: the call polls until completion, can return a results_pending status, and yields a specific result shape. It omits whether this persists a search record (siblings get_expert_search/list_expert_searches imply it does), timeout behavior, and whether repeated identical queries create duplicates.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core action, then the return shape, then the edge-case routing, in three sentences with no filler. The field enumeration earns its space because no output schema exists.

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?

Because there is no output schema, the description must describe returns and it does so thoroughly, plus it covers the pending-status escape hatch. Minor gaps remain around empty-result behavior and how long polling may take before giving up.

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?

Only one parameter exists and schema coverage is 100% with a strong inline example, so the schema already does the work. The description adds only the framing that the query is natural-language, which is already implied by the parameter description.

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 — find experts matching a natural-language query — and names the engine behind it. It is clearly separable from get_expert_search (retrieves already-computed results) and list_expert_searches (enumerates past searches).

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 a clear condition for the follow-up path: if status is results_pending, call get_expert_search instead of re-running. It does not explicitly say when to prefer this over lookalike siblings such as user_search or keyword_search, so the guidance stops short of full alternative routing.

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