stop_course_browser

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

With no annotations, the description must carry the behavioral burden; it does disclose the key side effect (Playwright process is stopped) and the safety boundary (host browsers untouched). It omits whether the call is idempotent when no browser is running, whether it errors or no-ops in that case, and whether in-flight work is discarded.

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?

One sentence, front-loaded with the action and the resource, with the disambiguating clause placed immediately after. Nothing is repeated and nothing is padding.

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 simple: no params, an output schema that covers return values, and no annotations needing reconciliation. The description covers scope and side effect adequately; only the not-running/idempotency edge case and its relationship to start_course_browser are left unstated.

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?

Zero parameters, so there is nothing for the description to disambiguate and the baseline of 4 applies. No parameter-related omission exists.

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 names a specific verb pair and resource ('Close the owned browser and stop Playwright'), which is unambiguous about what the tool does. The parenthetical scopes it away from host browsers, but it never names the counterpart tool (start_course_browser) or any sibling it must not be confused with, so differentiation is implied rather than explicit.

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?

'Never touches host browsers' gives a when-not boundary, but there is no stated condition for when this should be called (after a course browser session, on cleanup, on failure), no prerequisite that a browser must first be started, and no alternatives named among the many stop_*/close_* siblings.

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