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

With no annotations provided, the description carries the full burden and handles it well. It discloses that OAuth tokens are cleared, the status flips to disconnected, a typed user confirmation is required, the action is not reversible via the agent, the user must redo OAuth, and all flow automation on the account stops. This is unusually transparent about side effects.

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?

Every sentence earns its place. The description starts with the core action and effect, gives real user utterances, then delivers call-level instructions, confirmation behavior, and irreversible consequences. It is dense but not bloated, well ordered, and free of filler.

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?

The description is very complete for a disconnected mutation tool: it covers invocation, parameter selection, confirmation, reversibility, and downstream effects. It lacks an explanation of what the accountId parameter is for and does not describe the response or error behavior, but since no output schema exists and the operational context is richly covered, the definition is strong with only a minor residual gap.

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?

The schema has three parameters with zero description coverage, so the description must compensate. It gives clear meaning to platform ('the platform they named IS the target') and handle ('narrows it when several are connected'). However, accountId is not explained at all, leaving one of three parameters undocumented. Overall, it adds strong semantic value beyond the bare schema, with a minor gap.

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 description clearly states the tool's function: 'Disconnect a connected social account — clears OAuth tokens, flips status to

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 provides explicit when-to-use guidance via example user intents, instructs that the platform named by the user should be passed directly on the first call, and explicitly warns against calling list_accounts first. It also explains when to use the handle parameter and notes that a typed user confirmation is required, which is essential operational guidance.

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