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

Annotations already declare destructiveHint=false, idempotentHint=true and openWorldHint=true, so safety and side-effect profile are largely covered; the description usefully adds that no settings change, no secrets are returned, and the exact return shape with the three status values. However it does not explain why readOnlyHint is false despite 'does not change any settings' (presumably the live external call), which is the one place an agent might be confused.

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?

Front-loaded with purpose and behavior before the routing and parameter notes, and nearly every clause carries actionable information. It is dense and long for a two-parameter tool, and the parenthetical asides make it slightly harder to scan than it could be.

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?

With no output schema, the description supplies the return contract itself, defines the 'not_connected' edge case, states the no-secrets guarantee, and tells the agent what to do on each error status. Nothing needed to invoke or interpret this tool correctly is missing.

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 only 50% (project_id is undocumented in the schema), and the description compensates fully: it explains that ad_id IS the connection handle, that ad_id comes from list_ads, and that project_id is optional with the specific 'project_id_required' failure mode routed to list_projects. That is meaning well beyond the schema.

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?

States a specific verb and resource ('Verify that an ad integration's saved connection still works') and immediately clarifies the mechanism ('runs a live connectivity/auth check against the ad channel right now'). The 'ad' qualifier plus the explicit 'no separate handle is needed' note distinguishes it from test_marketplace_connection and test_order_connection.

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?

Gives concrete trigger conditions ('when an ad looks connected but items fail, or after credentials/OAuth may have expired') and routes the agent away from wrong actions: use clone_ad rather than expecting a channel transfer, and send the user to the browser/Koongo UI rather than calling configure_ad_step to set credentials. Alternatives and exclusions are both explicit.

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