MCP Server for OpenMetadata

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

With no annotations provided, the description carries the full burden of behavioral disclosure but offers almost none. 'Test event subscription destination' implies a diagnostic/validation operation but doesn't specify whether this is a read-only check or has side effects, what permissions are required, what happens during testing, or what constitutes success/failure. For a tool with a nested object parameter and no output schema, this leaves critical behavioral aspects completely undocumented.

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?

The description is extremely concise at just three words, which is efficient and front-loaded. However, this conciseness comes at the cost of being under-specified rather than appropriately sized. While there's no wasted language, the description fails to provide the necessary information that would justify its brevity in a tool with complex parameters and no annotations.

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?

Given the complexity (nested object parameter with 0% schema coverage, no annotations, no output schema), the description is completely inadequate. A testing tool typically requires understanding what's being tested, what input format is expected, what the test does, and what results to expect. The current description provides none of this context, leaving the agent unable to properly understand, select, or invoke this tool compared to the many other testing and event-related tools in the system.

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?

The schema has 0% description coverage for its single parameter 'destination_data', which is a nested object with no documented properties. The description provides absolutely no information about what this parameter should contain, what format it expects, or what 'destination data' means in context. With such low schema coverage and no compensatory explanation in the description, the agent has no meaningful guidance about how to construct valid input for this tool.

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 'Test event subscription destination' is a tautology that essentially restates the tool name 'test_event_destination' with minimal elaboration. It indicates the tool involves testing something related to event subscriptions, but doesn't specify what action is performed (e.g., validate, verify connectivity, send test payload) or what resource is being tested. Compared to sibling tools like 'create_event_subscription' or 'delete_event_subscription', this lacks the specific verb that would clarify its distinct purpose.

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 provides no guidance on when to use this tool versus alternatives. There's no mention of prerequisites (e.g., needing an existing event subscription), appropriate contexts, or what makes this tool different from related tools like 'test_service_connection' or 'get_subscription_status'. The agent receives no help in determining when this specific testing operation is needed versus other testing or diagnostic tools in the system.

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