tab_close

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

Annotations already flag destructiveHint=true and idempotentHint=false, but the description adds the cascading consequence ('every pane process in it'), which is the key thing an agent cannot infer from a flag. It does not restate irreversibility or confirmation behavior, which keeps it below a 5.

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, zero padding, with the destructive scope stated before the safety constraint. Every clause earns its place.

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 destructive mutation with an output schema present, the description covers blast radius and ownership limits, which is most of what an agent needs. The remaining gap is sourcing the tab_id, which nothing else documents.

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 single parameter tab_id has 0% schema description coverage, so the description carries the full burden and adds nothing: no id format, and no pointer to tab_list as the way to obtain a valid tab_id. The word 'tab' implies the resource but nothing more.

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?

Specific verb (close) plus resource (tab) and an explicit scope statement: 'every pane process in it'. The resource noun separates it from pane_close and workspace_close among the siblings, though those alternatives are never named.

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?

'Only close tabs you created or the user named' is a concrete when-not-to-use rule that rules out opportunistic closing of tabs the agent doesn't own. It stops short of naming alternatives such as pane_close for closing a single pane instead of a whole tab.

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