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

Annotations already declare readOnlyHint=false / openWorldHint=true / destructiveHint=false, and the description adds real context: it browses a LIVE site, can actively click/type through flows in drive mode, and reports the journey taken. It stays silent on runtime cost/duration and on which controls are blocked without allow_external_actions (that only appears in the schema), which is the remaining gap.

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?

Front-loads the core action and outcome, then layers the drive-mode nuance and product family in two short follow-ups. Every clause carries information; only "Part of Agentic Eyes" is close to filler, though it does hint at related export/report siblings.

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 9-parameter, no-output-schema tool with open-world behavior, the description is strong: it specifies the report's contents as the de facto return value and explains drive mode. It doesn't address run duration/cost or how the result is retrieved or exported later (export_agentic_eyes_report exists), leaving a modest gap.

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%, so the baseline is 3; the description only elaborates on `drive` and gives friendly persona names ("Sally, the Dreaming Planner, or the Worst-Customer-Ever") to complement the schema's slugs. It adds nothing on evaluation_mode, allow_external_actions, max_steps, or the mandatory context 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?

Names a concrete verb+resource (browse a live site as a specific AI persona) and enumerates the report contents, so the agent knows exactly what comes back. It never explicitly contrasts itself with near-siblings like run_persona_consensus, run_agent_eval, or start_ai_crawl, so disambiguation is inferred rather than stated.

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?

"With drive=true the persona actually clicks through a multi-step flow (not just the landing page)" gives one useful usage distinction, plus the persona examples hint at when to pick a specific persona. There is no explicit when-to-use/when-not framing and no routing to alternative tools such as run_persona_consensus for multi-persona runs.

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