Quit Firefox

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

Annotations only say destructive/not-read-only; the description adds real consequences: the browser is torn down, the server loses its connection until Firefox restarts, and the one-active-BiDi-session limit means this call fails with 'Maximum number of active sessions' in the leaked-SIGKILL state. That is precisely the kind of runtime behavior annotations cannot convey.

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?

Front-loaded with the action and its consequence, then the limitation, then the value proposition — good ordering. It runs long for a zero-param tool and 'use it deliberately' plus the closing sentence restate the caution slightly, but no sentence is pure filler.

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?

With no parameters, no output schema, and only coarse annotations, the description carries the full burden and meets it: it covers the effect, the loss of connection, the known limitation, and the recovery path. An agent has everything needed to decide to call it or not.

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 has zero parameters, so there is nothing to disambiguate; the baseline for a 0-param tool is 4. The description adds no parameter guidance because none is needed.

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?

States a concrete verb and resource ('Ask the connected Firefox to exit (browser.close)') and is clearly distinguishable from the many browser_close_tab / browser_close_window / browser_*_session siblings. The scoping is unambiguous: whole-browser shutdown, not tab or window teardown.

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 says when to use it ('a clean, orderly shutdown while a session IS available, instead of killing the process') and when it will not work ('it CANNOT rescue an already-leaked session ... only restarting Firefox externally helps'). It even names the failure condition that diverts the agent to an out-of-band action.

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