session_disconnect

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

Beyond the annotations (destructiveHint=true, readOnlyHint=false), the description reveals important behaviors: state is preserved, reconnection is allowed, a bare call is non-destructive, sessions with unreadable users are refused, and the operation is audited. This contextualizes the destructiveness and gives the agent a safe interaction pattern.

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 dense but every sentence earns its place: the action and key behavior in the first line, the distinction from logoff, the safe-call workflow, the refusal edge case, and the user-consent directive. It is front-loaded with the essential purpose and safety guidance.

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 tool without an output schema, the description covers everything an agent needs to invoke it correctly: how to identify targets, what the default call does, how to get consent, what happens on refusal, and auditability. The target parameter is documented in the schema, so no critical gap remains.

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%, so the baseline is 3. The description adds meaning by clarifying the relationship between session_ids and user ('Identify by session_ids OR user') and by explaining the confirm parameter's effect (bare call vs. actual disconnect). This goes slightly beyond the schema descriptions.

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 and resource: 'Disconnect Horizon session(s)'. It immediately distinguishes itself from the sibling 'logoff' by noting state is preserved and the user can reconnect, so an agent can tell it apart from session_logoff without opening that tool's definition.

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 explicitly contrasts with logoff ('Less disruptive than logoff') and details the safe usage workflow: a bare call returns blast_radius without side effects, the agent should show this to the user and wait, and confirm=True should only be set after user approval. This is actionable when-to-use guidance that prevents premature destructive action.

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