browser_cleanup_session

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

With no annotations, the description carries the full burden and does real work: it discloses that dry_run defaults to preview, that dry_run=false either removes the finished record or terminates only an identity-verified IEDriver, that it waits for owner exit, and enumerates what it will never kill (Edge, unknown/live owners, untracked processes). It stops short of stating permission requirements or what a preview returns.

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?

Three dense sentences with zero filler, ordered from the safe default outward to the destructive path and then to the hard safety exclusions. Every clause carries operational meaning; nothing is repeated from the schema.

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 annotations, no output schema, and two undocumented parameters, the description covers the mutation risk, the safety guards, and both parameter behaviors adequately. It leaves out what the preview output looks like and any permission or concurrency caveats, which are the only remaining gaps for a destructive-capable tool.

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 coverage is 0%, so the description must carry both parameters and it largely does: dry_run's default-true preview versus false-side-effect semantics are spelled out, and session_id is constrained to an "exact" id sourced from browser_sessions (ruling out prefixes or guesses). Minor gap: the description doesn't clarify what happens when dry_run=false targets a live/incomplete session.

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 action (cleanup/removal or termination) on a specific resource (a browser session record and its IEDriver), and the default preview behavior is front-loaded. It implicitly separates itself from browser_sessions by telling the agent to pull the session_id from there, but it never names browser_close, the closest sibling, so the differentiation is partial.

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?

"Use an exact session_id from browser_sessions" gives a concrete sourcing rule, and "Preview cleanup by default" tells the agent what a naive call will do. However, there is no explicit statement of when to choose this over browser_close or browser_close_window, and no stated precondition such as the session being finished beyond the passing mention of "a finished record".

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