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

Annotations mark this destructive, idempotent, open-world, and non-read-only, but the description adds genuinely new behavioral context: it requires the integrations:write scope, the first call mutates nothing, unknown fields are refused by name, and the confirmation token must be replayed. That is real value beyond the structured hints.

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?

Four tight sentences front-load purpose and permission, then the two-call protocol. Every sentence carries information, though 'it checks the arguments as the change would' is slightly awkward phrasing that could be simpler.

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 two-step tool with no output schema, the description covers the safety-critical flow, the token contract, and the permission needed. It does not say what the summary contains or what disconnection actually does to existing data, which an agent might want before presenting to a user.

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 50% because provider is undocumented, but the description compensates by explaining the confirm_token lifecycle in detail: omit on the first call, supply the token from the first call along with the identical arguments on the second. Only the provider field's expected values remain unstated.

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 first sentence names a specific verb and resource ('Disconnect a calendar or SoundCloud'), and the provider field narrows the scope to integration providers rather than arbitrary resources. This clearly separates it from siblings like list_integrations, sync_integration, and import_soundcloud.

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?

It gives explicit procedural guidance: call twice, the first call is a no-op validation, show the summary to the person, then re-call with confirm_token. It stops short of saying when not to use it (for example, when only pausing sync is intended) or naming alternative tools.

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