end_remote_application

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

With no annotations provided, the description must carry the full behavioral burden, and it does. It explicitly says the application will be force-closed, warns that unsaved data will be lost, and instructs the agent to confirm with the user. This is exactly the critical destructive behavior a model needs to call this tool safely. It doesn't describe every edge case, but the core irreversible impacts are disclosed.

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 remarkably concise: two sentences state the purpose and a short caution block communicates the danger and the required user confirmation. There is no filler or redundant re-explanation of the tool name, and the critical warning appears directly after the action statement, earning every character.

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 tool is 2-parameter, has full schema coverage, and includes an output schema, so the description does not need to explain return values. It fills the safety gap provided by zero annotations with the caution about force-closing and data loss. It could still be slightly more complete by explicitly stating that the session and other applications remain unaffected, but this is largely inferable from the wording.

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 description coverage is 100%, and the input schema already provides meaningful parameter descriptions—including an example of how to discover remote_application_id via diagnose_session. The tool description itself adds no parameter-specific semantics, so it remains at the standard baseline given the adequate schema coverage.

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 ('Terminate') with a specific resource ('a remote application') and scopes it to 'running in a session.' This clearly distinguishes it from sibling tools that operate on whole sessions (e.g., disconnect_sessions, logoff_sessions, reset_or_restart_sessions). An agent can immediately understand this tool ends an individual application rather than a session.

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 the tool should be used when one wants to terminate a specific remote application, but it does not explicitly contrast this with alternatives such as logoff_sessions or mention when not to use it. The caution about confirming with the user is a behavioral guideline, not a usage selector. The semantics are clear enough to infer the intended use, but the description stops short of giving explicit when/when-not guidance.

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