session_disconnect

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

Beyond the annotations (destructiveHint, readOnlyHint), the description adds critical behavioral context: state preservation and reconnectability, the blast-radius preview behavior enabled by confirm=False, auditing, and substring matching for user. This significantly enriches the agent's understanding of consequences.

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 concise and front-loaded, with the purpose stated in the first line, followed by a valuable comparison and then an organized Args list. No sentence is wasted; the structure makes it easy to parse.

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 covers the core behavior, parameter semantics, safety implications, and alternative choice. However, since there is no output schema, it would benefit from a note about what is returned after the action or in preview mode, and possible error/failure behavior; otherwise the agent may be uncertain about expected results.

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?

Despite 0% schema description coverage, the description compensates fully by explaining all four parameters: session_ids, user (with substring match semantics), confirm (preview vs. apply), and target (source from config.yaml and default behavior). This is exactly what an agent needs to invoke the tool correctly.

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 opens with a specific verb+resource ('Disconnect Horizon session(s)') and immediately clarifies the behavioral nuance ('state preserved, the user can reconnect'), which both defines the action and differentiates it from the sibling tool session_logoff. It is clear, specific, and unambiguous.

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 gives practical guidance: 'Less disruptive than logoff' signals when to prefer this tool over the sibling, and it explains how to identify sessions (by session_ids OR user) and how confirm controls preview vs. apply. However, it does not explicitly state a 'when not to use' scenario beyond the implied contrast with logoff.

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