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

Annotations already declare destructiveHint=true and idempotentHint=true, so the description's main added value is scoping the blast radius: browser sessions are terminated while API keys and connected assistants are left alone. That is exactly the 'what gets destroyed and what doesn't' context the annotations cannot express. It stops short of saying whether the action is reversible or whether the user is notified afterward.

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 short sentences, front-loaded with the action and its scope, then the exclusion, then the usage gate. No filler and no repetition of the title or annotations.

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 parameterless destructive tool with rich annotations, the description covers scope, exclusions, and invocation conditions well. The only gap is that no output schema exists and the description says nothing about what the call returns (e.g., how many sessions were ended) or whether confirmation is surfaced.

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 there is nothing to disambiguate and the baseline applies. The description correctly adds no parameter talk that would be redundant.

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 first sentence names a specific verb (ends) and resource (every browser session signed into the account portal) with explicit scope ('every... at once, wherever it is signed in'). The second sentence draws the boundary against adjacent concepts, so an agent can distinguish it from revoke_api_key and assistant-unlinking tools in the sibling list.

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?

Gives an explicit trigger ('Offer it when the user is worried a browser session is not theirs') plus an explicit gate ('Call it only when the user asks for it in their own message'), which is a real when-not condition. It also routes the adjacent need elsewhere by noting API keys and connected assistants have their own revoke path.

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