Mentornity

Find ventures (startups, teams)

search_ventures

Read-onlyIdempotent

The ventures (startups, teams: the programme's groups) on the programme's ventures page, as the person may see them there; refused where the programme does not show that page to the person. Narrows by words in the name, description and profile answers (query), and by one profile question and its answer (question + answer, for example question "sector" and answer "edtech"). Each venture comes with its venture_id, description, website, its answers to the programme's profile questions and, for a mentor, how many meetings the person has held with it and when the last one was; only_met lists just the ventures the person has met. The first page also lists the profile questions that can narrow the list, with their options. Members, LinkedIn and the full answers are in the venture's profile (role group).

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": {
      "program": "<program>"
    },
    "name": "search_ventures"
  }
}

Input Schema

Name	Required	Description
`page`	No	Page, from 1 (20 per page).
`sort`	No	Order: name, newest first, or most recently met first (default last_met with only_met, otherwise name).
`query`	No	Words that each venture's name, description or answers contain (optional).
`answer`	No	With question: an option of that question, or words its answer contains.
`program`	Yes	Id or domain of one of the person's programmes.
`only_met`	No	Only ventures the person (a mentor) has held meetings with.
`question`	No	A profile question to narrow on: its question_id or words from it, such as "sector" or "stage" (optional).

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 12, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), and the description adds genuine value on top: permission-gated access per programme, the full shape of each venture record, mentor-specific meeting counts and last-meeting date, and the fact that the first page lists filterable profile questions with their options. It stops short of covering pagination limits and error behavior, so a 4 rather than 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?

The resource and visibility constraint are front-loaded, and almost every clause carries information (record contents, filtering modes, mentor extras). It is a dense, multi-clause paragraph with long semicolon chains that take effort to parse, which costs it a point but there is little outright redundancy.

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 7-parameter, read-only search with no output schema, the description supplies what the schema cannot: what a result contains, the mentor-only fields, the permission gate, and the first-page question listing. Sort defaults and page size are left to the schema, which documents them adequately, so nothing essential is missing.

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 earns more by explaining how parameters interact: query matches across name, description and profile answers; question pairs with answer and accepts a question_id or words like "sector"; only_met restricts to ventures the person has met. The concrete "sector"/"edtech" example clarifies the question+answer contract beyond the schema text.

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?

The description names the resource precisely and glosses it for disambiguation ("startups, teams: the programme's groups"), plus what is returned, so an agent can tell this apart from search_mentors or search_mentees. It lacks an explicit verb (find/list) and relies on the title to supply the action, which keeps it just short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives real conditions: results are the ventures as visible on the programme's ventures page, and the call is "refused where the programme does not show that page to the person," plus an example of the question+answer narrowing pattern. It never says when to prefer this over the sibling search tools or what to do when the page is not available, so guidance is implied rather than explicit.

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

All Mentornity 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.

Resources

Need Help?