test_connection

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

No annotations are provided, so the description carries full burden. It indicates the tool executes diagnostic tests and identifies root causes, but it does not disclose whether the test is read-only, has side effects, or requires specific permissions. This is adequate but incomplete for a diagnostic mutation-like action.

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 two sentences: the first clearly states the purpose, and the second elaborates on use cases. It is front-loaded and efficient, though slightly verbose with multiple examples.

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 simple tool (one parameter, output schema exists), the description covers purpose and usage contexts well. It does not explain return values, but the output schema likely handles that. Lacks mention of prerequisites or side effects, but overall adequate.

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?

With 100% schema description coverage and only one parameter ('connection_id'), the description adds no extra meaning beyond the schema's documentation. 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 clearly states the verb 'test' and the resource 'Fivetran connection', explicitly defining its role in diagnosing connectivity and configuration issues. It distinguishes itself from sibling tools like 'get_connection_status' by emphasizing active diagnostic testing.

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 clear contexts for use: when syncs fail, proactive health validation, and incident response. However, it does not explicitly state when not to use or compare to alternatives like 'get_connection_status', so some guidance is implied but not exhaustive.

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