Remove a monitored instance from a device datasource to stop data collection. Provide device, datasource, and instance IDs for deletion.
Delete a monitored instance from a datasource on a device (requires write permission)
| Name | Required | Description | Default |
|---|---|---|---|
| device_id | Yes | Device ID | |
| instance_id | Yes | Instance ID to delete | |
| device_datasource_id | Yes | Device-DataSource ID |
Changes observed during successful MCP inspections.
v4.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=true, so the description does not need to restate those. It adds value by specifying the authorization requirement ('requires write permission'), which is concrete behavioral context not captured in the annotations. It does not contradict the annotation profile.
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?
One short sentence contains the action, the object, and the key precondition with no wasted words. Everything included is relevant and front-loaded.
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 delete operation with three required parameters, complete schema descriptions, and annotations covering destructive and safety traits, the description is reasonably complete. It covers authorization and the object of deletion; no output schema exists, so return values need not be described.
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 description coverage is 100%, and each parameter has a clear, if terse, description. The tool description does not add meaning beyond what the schema already provides; the resource phrase maps cleanly to the three identifiers but adds no syntax, relationships, or formatting details.
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 states a specific verb ('Delete') and a precise resource ('a monitored instance from a datasource on a device'), which clearly distinguishes this from sibling tools like add_device_instance, update_device_instance, get_device_instances, delete_device, and delete_datasource. The parenthetical about write permission also reinforces the nature of the operation.
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?
The description implies its use via the word 'Delete' and adds the prerequisite 'requires write permission', but it never explicitly states when to use this tool versus alternatives like delete_datasource or delete_device. There are no exclusions or routing hints that would help an agent choose between related delete operations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.