tab_action

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

The description goes well beyond the annotations by detailing that close discards unsaved content and cannot be undone, that reload/navigation drop injected CSS, emulations, and page hooks, and that duplicate has special restrictions (works on chrome-untrusted://, lands in source window). It also discloses that discard replaces the tab id, making saved ids stale. These are substantive behavioral traits not captured by the readOnlyHint/destructiveHint annotations, and there is no contradiction.

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?

The description is front-loaded with a succinct summary of actions, and each sentence conveys unique operational details. The long sentence about duplicate is dense but contains critical, tool-specific facts. It is appropriately sized for a multi-action tool, though it could be slightly tightened without losing value.

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?

Given the tool's complexity (9 enum actions, multi-action behavior), the description does a good job covering destructive consequences (close), side effects (reload), edge cases (duplicate), and id-staleness (discard). However, it entirely omits the mute/unmute actions and does not explain back/forward history semantics or return values for other actions, leaving some gaps for an agent relying solely on this description.

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 input schema already provides 100% coverage for all three parameters, including enum descriptions for actions and notes on bypass_cache and tab_id. The description adds meaningful extra context not in the schema, such as bypass_cache being 'optional cache bypass,' duplicate's environment restrictions, and discard's id replacement. This elevates it above the baseline 3.

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 begins with 'Tab lifecycle' and enumerates specific operations (close, activate, reload, back, forward), making the general purpose clear. It distinguishes duplicate from the sibling create_tab by noting it works where create_tab is forbidden. However, it omits the mute and unmute actions that appear in the enum, and does not contrast back/forward with the navigate sibling, so the full scope is somewhat incomplete.

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?

The description provides explicit guidance for duplicate as an alternative to create_tab and warns that close is irreversible and may affect a tab the user is working in. It also explains side effects of reload/navigation that should inform when to use this tool. It does not, however, offer explicit when-not-to-use guidance for back/forward versus navigate, or for activate/reload in all contexts.

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