shell_close

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

Beyond the annotations (idempotent, non-destructive), the description discloses an important side effect: the VM remains locked after the call and requires a separate vm_unlock. It also identifies that broker resources are released. This adds meaningful behavioral context beyond what annotations already provide.

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 no filler: the first states the action, the second gives the critical postcondition and next step. The most important information is front-loaded.

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 simple close action with only two parameters and no output schema, the description is complete enough: it explains the cleanup effect, the lock behavior, and the follow-up action. It could be slightly richer by mentioning what happens when called on an already-closed or invalid session, though idempotentHint partially covers that.

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 covers vm_name but leaves session_id undocumented. The description ties session_id to an interactive shell session and to the VM lock, which adds useful context. It does not state where session_id comes from (e.g., shell_start) or its format, so it only partially compensates for the schema 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 uses a specific verb and resource: 'Release broker resources for a completed interactive shell session.' It clearly identifies the tool as a session-close cleanup operation. It doesn't explicitly differentiate from the sibling shell_terminate, but 'completed' and 'release' make the distinction reasonably clear.

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 states when to call the tool: after the interactive shell session is completed, and before the VM lock is released. It also explicitly directs the caller to vm_unlock, giving a clear sequence. It doesn't mention alternatives such as shell_terminate for active sessions, so it lacks explicit exclusions.

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