launch_app

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

Exceeds annotations by detailing side effects: starts a process, Glasswarp tracks it and closes it on end_session. Annotations only indicate openWorldHint and destructiveHint; the description adds specific lifecycle and usage behavior (wait after launch), which is highly valuable for an agent.

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?

Four sentences, front-loaded with purpose, side effects, usage examples, and a critical caveat. Every sentence contributes unique information with no redundancy or fluff.

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 tool with no output schema, the description adequately covers purpose, side effects, parameter semantics, and usage guidance. No significant gaps remain for an agent to select and invoke this tool correctly.

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%, so baseline is 3. The description adds minimal extra meaning: clarifies path_or_name can be name on PATH or absolute path, and mentions optional args, but schema already provides examples for args. Doesn't substantially improve understanding beyond schema.

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 clearly states the verb 'launch' with a specific resource ('executable on the remote Windows rig') and includes examples (notepad.exe, mspaint.exe, chrome) that distinguish it from sibling tools like click_target, type_text, etc.

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?

Provides explicit usage context ('Use for notepad.exe, mspaint.exe, chrome with URL args, etc.') and a critical behavioral guideline ('Wait/re-observe after launch before clicking — do not assume the window is focused immediately'). Could be improved by explicitly stating when not to use, but the examples and sibling list imply alternatives.

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