datalens_connections_deleteDelete a DataLens connection by ID. Datasets built on it lose their source, and charts keep referencing its id; deletion cannot be undone via API.
Delete a connection; the datasets built on it lose their source.
The API has no way to bring it back, and a chart that reads through it keeps naming its id (measured).
| Name | Required | Description | Default |
|---|---|---|---|
| connection_id | Yes | Connection id. |
Changes observed during successful MCP inspections.
v0.122.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true and idempotentHint=false, so the safety baseline is covered. The description nonetheless adds real value beyond them: it specifies what gets damaged (datasets lose their source), that the action is unrecoverable ('no way to bring it back'), and a referential side effect (charts keep naming the deleted id). The trailing '(measured)' is an unexplained artifact that slightly muddies otherwise strong disclosure.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two tight sentences with the action front-loaded and the consequence trailing. The stray '(measured)' parenthetical is wasted tokens and the only blemish on otherwise efficient structuring.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a single-parameter destructive delete with no output schema, the description plus annotations cover the essentials: what the tool removes and that it cannot be undone. It is nearly complete, missing only explicit permission/authorization requirements.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with a single documented 'connection_id' parameter, so the schema carries the full burden. The description only obliquely references the id ('keeps naming its id') and adds no format or constraint detail. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description gives a specific verb+resource ('Delete a connection') and immediately qualifies it with the consequence ('the datasets built on it lose their source'). This cleanly distinguishes it from the sibling get/create/update connection tools without ambiguity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no explicit when-to-use, when-not-to-use, or alternative routing. The irreversibility note implies caution, but it never tells the agent under what conditions deletion is the right choice versus, say, datalens_connections_update or detaching datasets first.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.