Mondovo

Test a data source address

test_data_source_connection

Idempotent

Fetch a PUBLIC endpoint or feed once and report how many items it returned, the fields in a sample item and — with content_key — a suggested field mapping onto that section. Saves nothing, but it is a real request to the outside address. The address must be public http(s) and need no key; an endpoint that answers 401/403 needs a key, which is connected in the site's Data Sources settings, never in a conversation. Always test before connect_data_source.

Input Schema

Name	Required	Description
`site_id`	Yes	The site, from list_sites
`user_goal`	No	Optional: the user's goal behind this call, in one short sentence of plain words (e.g. "add a page so customers can book tables"). No names, emails or other personal details.
`content_key`	No	The section you intend to fill, from list_bindable_content_keys
`source_type`	Yes	"rest_api" for any JSON/HTTP endpoint, "rss" for an RSS/Atom feed
`endpoint_url`	Yes	The full public address to fetch
`response_path`	No	Dot-path to the list inside the JSON, e.g. "data.plans". Omit for a top-level list or a feed.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 30, 2026

addedInput schema / properties / user_goal

Added value: +{
+  "description": "Optional: the user's goal behind this call, in one short sentence of plain words (e.g. \"add a page so customers can book tables\"). No names, emails or other personal details.",
+  "type": "string"
+}

First observedOct 19, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Adds meaningful behavior beyond annotations: saves nothing, but performs a real external request; requires public addressing with no key; and explains what a 401/403 means. This is consistent with readOnlyHint=false and openWorldHint=true without contradiction.

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?

Four dense sentences, front-loaded with the outcome and immediately followed by the safety constraint and workflow rule. No sentence feels redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

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 carries the return-value burden and does so clearly: item count, sample fields, and optional suggested mapping. It also sufficiently covers external side effects and auth prerequisites for a 6-parameter tool.

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 baseline is 3, but the description adds cross-parameter meaning: content_key triggers a suggested field mapping, and endpoint_url must be public with no key. It does not mention response_path or user_goal, but the schema already documents those fully.

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: fetch a public endpoint or feed once and report item count, sample fields, and an optional suggested mapping. It clearly distinguishes itself from connect_data_source by being a non-persisting test rather than a connection.

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

Usage Guidelines5/5

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

Explicitly instructs to always test before connect_data_source. It also states the public http(s), no-key constraint and routes 401/403 cases to Data Sources settings rather than conversation-provided keys.

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

All Mondovo 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?