close

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

With no annotations, the description carries the burden and does disclose the key behavioral fact: this kills all tabs AND the stdio server, i.e., it terminates the session and any unsaved page state. It omits whether that is recoverable, and it never explains how the `tab` parameter interacts with an all-tabs shutdown.

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?

Two short sentences: the scope-defining action first, the sibling redirection second. Nothing wasted, nothing buried.

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 one-parameter shutdown tool with no output schema, the essential facts (what dies, which sibling to use instead) are present. The unresolved tension between 'closing all tabs' and the `tab` parameter is the one thing an agent could still get wrong.

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 100% and the `tab` parameter is already documented there as 'tab id, defaults to current', so the description has no obligation. However, it adds no meaning and arguably conflicts with the schema by implying every tab closes regardless of the parameter.

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 specific verb ('shut down') and the target ('Bruster'), plus the concrete effect of closing all tabs and the stdio server. It is clearly distinguished from the sibling close_tab. The presence of a `tab` parameter is not reconciled with the 'all tabs' framing, which slightly muddies what is actually being closed.

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 routes the agent: 'Use close_tab to close only one tab' gives the when-not case and names the alternative. It does not say when full shutdown is preferable (e.g., end of session vs. error recovery), so it stops short of a full 5.

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