session_logoff

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

Annotations mark this as destructive, and the description transparently explains the blast radius preview, the need for confirm=True to apply, the profile write-back side effect, and the audit trail. This goes well beyond the annotation hints, helping the agent understand the full impact.

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 about 120 words and is efficiently structured: a one-line summary, then targeting and confirmation workflow, then parameter details. No filler or redundant repetition of the schema's titles.

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, multi-mode tool with no output schema, the description covers safety workflow, parameter semantics, and operational context. The only minor omission is an explicit return-value description, but the preview behavior is already described. Overall, it is a complete description.

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 input schema has zero descriptions, and the description compensates fully: it explains session_ids come from session_list, user is a substring match that refuses on no match, confirm controls preview vs apply, and target selects the Horizon endpoint from config.yaml. Every parameter is given meaningful context.

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 'Force-logoff Horizon session(s)' — a specific verb and resource — and further clarifies it 'kicks the user, triggers profile write-back,' distinguishing it from softer operations like session_disconnect. The targeting modes (by session_ids or user) also make the tool's function unmistakable.

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 clear operational guidance: identify targets by explicit session_ids or by user, and preview with confirm=False before applying with confirm=True. However, it does not explicitly compare itself to session_disconnect or other session tools, so the 'when vs alternatives' exclusion is missing.

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