inspector_highlight

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

Annotations already indicate readOnlyHint=false, destructiveHint=false, and idempotentHint=false, so the description doesn't need to repeat those. However, it adds minimal context—mentioning 'optional selector hints' but not what happens to the session when mode is activated, whether navigation occurs, or if there are side effects. Given the low bar from annotations, this is acceptable but not enriched.

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?

A single, front-loaded sentence with no fluff. The action and subject are immediately clear, and it avoids redundant detail. This is a model of conciseness.

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?

The description omits key contextual details: it assumes an 'active browser session' but doesn't state that a session must already exist or how to ensure one. There is no mention of return values or what the agent should do after activation. Given no output schema and no required parameters, the description leaves the agent with gaps about preconditions and expected outcomes.

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 description coverage is 100%, with each parameter already having a clear description. The tool description's phrase 'optional selector hints' aligns with targetHint but adds no new meaning beyond the schema. Since the schema does the heavy lifting, a baseline of 3 is appropriate.

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 clearly states a verb ('Activate') and a resource ('inspect/highlight mode') tied to a browser session. It distinguishes from siblings like browser_open and task_execute by focusing on a mode activation rather than opening or executing. However, 'inspect/highlight mode' is slightly underspecified—what it does beyond highlighting isn't elaborated, but the purpose is still discernible.

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?

No guidance is provided on when to use this tool versus alternatives. It does not mention prerequisites (e.g., an existing browser session), nor does it contrast with browser_open or task_execute. The agent must infer context from the description and sibling names, which is insufficient.

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