glass_stop

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

With no annotations provided, the description carries the full burden and does so excellently. It discloses the graceful-close-then-terminate behavior, session-scoped data loss (logs, a11y ids), the persistence of saved baselines, the lack of resume, and the error condition when no session is running.

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 front-loaded with the primary action and then expands with necessary details about state, timing, and error behavior. Every sentence adds value, and despite its length, it remains focused and scannable.

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 state-mutating tool with no output schema, the description covers all essential context: what is affected, what persists, what does not, when it errors, and how to restart. It leaves no significant ambiguity for an agent deciding whether to invoke glass_stop.

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 tool takes zero parameters, so the baseline is 4. The description adds no parameter details because there are none, but it explains the tool's behavior comprehensively, which is the relevant semantic content for a parameterless tool.

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 'Stop the running app and end the session,' a specific verb and resource that clearly distinguishes this from sibling tools like glass_start. It also notes that only glass_start can run the app again, reinforcing its unique role as the session ender.

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?

Explicitly states when it is not needed ('Not needed between steps of a task') and that a session can be driven for as long as needed. It also identifies the alternative (glass_start) and clarifies that there is no resume, giving the agent clear decision rules.

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