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

Annotations already declare idempotent and non-destructive, but the description adds valuable behavioral details: this does not change settings, never returns secrets, reports a 'not_connected' status, and clarifies that credential/OAuth fixes happen only via the user in the UI. The readOnlyHint=false annotation is not contradicted because a live auth/connectivity check may still have side effects beyond settings.

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 dense but purposeful, front-loading the core purpose before covering return shape, edge cases, and user-only repair flows. While lengthy, nearly every sentence carries operational guidance, so the length is justified rather than redundant.

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 provides a full return contract including status values and their meaning. It also covers the not_connected edge case, the no-transfer constraint, the user-only credential repair path, and optional parameter handling—leaving no required decision ambiguous for correct invocation.

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%, but the description compensates by explaining that ad_id is both the integration ID and the connection handle, sourced from list_ads. For project_id, it clarifies that it is optional, when it becomes required, and how to discover it via list_projects—though it could have described the parameter's purpose more explicitly.

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 opening sentence uses 'Verify' with a specific resource and action: checking whether an ad integration's saved connection still works via a live connectivity/auth check. It clearly ties the tool to ads specifically and explains that the ad_id is the connection, distinguishing it from related connection-testing tools for marketplaces and orders.

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 explicitly states when to use the tool ('when an ad looks connected but items fail, or after credentials/OAuth may have expired') and when not to: do not retry configure_ad_step for credential fixes, route the user to the browser/UI instead, and clone the ad if a connection needs to move to another channel. It also provides fallback guidance for project_id with list_projects.

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