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

Annotations already flag destructiveHint=true and openWorldHint=true, but the description adds substantial value beyond them: it discloses the side effect on the external provider (webhooks created by Sendocado are removed first), the boundary of the operation (provider retains domains), and the downstream business impact (live campaigns stop sending). This is exactly the pre-invocation context an agent needs before running a destructive, non-idempotent 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?

Three tight sentences: what it does, what it destroys, what breaks as a result, plus a confirmation directive placed at the end as a call to action. Every clause carries information and the identity of the operation is 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 destructive single-parameter tool with no output schema, the description covers consequences and external side effects well. It does not say whether the sender configuration can be restored afterwards or what state the project is left in (e.g. whether get_sender will still resolve), which are the remaining questions an agent might have.

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 0% for the single required parameter. The description never mentions project_id, so it adds no meaning about which project's sender is disconnected or what identifier form is expected. However, the parameter is self-describing by name and there is only one, so the gap is minor rather than blocking.

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: 'Disconnect the project's email provider.' The scope is explicit (project-level sender disconnection), and the mention that 'the provider keeps its domains' implicitly distinguishes it from delete_sending_domain. An agent can tell this apart from update_sender or delete_sending_domain without opening either schema.

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 clear operational context ('Nothing can be sent until a sender is connected again, so live campaigns stop sending') and an explicit procedural instruction ('Confirm with the user first'). It does not name a sibling alternative (e.g. update_sender for configuration changes, or delete_sending_domain for domain removal), so routing guidance is clear but not exhaustive.

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