shell_terminate

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

Annotations already provide destructiveHint=true, readOnlyHint=false, and idempotentHint=false. The description adds value beyond those by disclosing a non-obvious behavioral trait: 'VM remains locked by this session; call vm_unlock when finished.' This tells the agent the session's lifecycle outlives the call itself and requires a follow-up action, which the annotations alone would not convey.

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?

Two sentences with zero filler. The primary action is front-loaded in the first sentence, and the critical follow-up (vm_unlock) is delivered in the second. Every word earns its place.

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 two-parameter tool with annotations present, the description covers the core action and the essential lock-lifecycle warning. The gaps are the undocumented session_id parameter semantics and the missing distinction from shell_close. No output schema exists, so return behavior is unaddressed, but this is a minor concern for a terminate-style tool.

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 only 50%: vm_name has a description, but session_id has only minLength: 1 with no semantic meaning. The description does not compensate by explaining what session_id is or where it comes from (e.g., the value returned by shell_start). An agent cannot know how to obtain or validate session_id from this definition.

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 states a specific verb and resource: 'Terminate a running interactive shell session.' This clearly identifies the operation. However, it doesn't differentiate from the sibling shell_close, which plausibly performs a similar shutdown action, leaving the agent to guess which one to pick.

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 implies usage context — terminating a session that is no longer needed — and gives a clear follow-up instruction to call vm_unlock. But it never states when to prefer this over shell_close, or any conditions that would exclude using it. Usage is implied by the lifecycle narrative rather than explicitly specified.

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