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

Annotations already flag destructiveHint=true and idempotentHint=true, but the description adds substantial context beyond them: the sign-in stops working immediately, re-authentication is required to reconnect, the action cannot be undone, an API key credential yields 403 because it names a workspace not a person, and an unclaimed sandbox workspace is also refused with 403.

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-loads the effect of disconnecting, then prerequisites and failure modes in a compact sequence. Dense but nearly every clause carries decision-relevant information; the dashboard parenthetical is slightly incidental.

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 single-parameter destructive mutation with no output schema, it covers effect, irreversibility, credential requirements, workspace prerequisites, and error codes (403). An agent has everything needed to call it and interpret failure.

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 100% and the property description already states 'id on a list_connected_apps result', so the description's 'Pass an id from list_connected_apps' largely restates the schema. The scoping note about limited-access connections is useful but is about authorization, not the parameter's format.

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?

Opens with a specific verb and resource ('Disconnect an app you connected by signing in') and explains the effect of disconnecting. It is clearly distinguishable from the sibling list_connected_apps, which it names as the source of the id.

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 explicit when-to-use routing ('Pass an id from list_connected_apps'), names an alternative surface for the same operation ('the dashboard can disconnect any, under Profile, Sessions, Connected apps'), and states the scoping rule that a less-than-full-access connection can only disconnect itself.

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