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

Beyond the readOnly/openWorld annotations, it discloses the shared-state model (browser, chat agent, and terminal all share one panel per conversation), the auth requirement ('Needs the read scope'), the long-poll cap of 25 seconds with re-call guidance, and the rollout caveat. These are exactly the traits structured fields cannot convey.

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 long and front-loads conceptual lore about what a panel is rather than the action itself. The rollout sentence ('The page draws it for the founder's account today...') and the shared-state sentence consume space without helping an agent decide to call the tool, though the final return-shape and scope sentence is efficient.

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 a read-only tool with a full output schema, documented parameters, and noted auth scope, the description covers the important gaps (waiting semantics, default conversation selection). What remains under-explained is the internal structure of 'tabs' and what a panel looks like when empty, though the output schema largely covers the return shape.

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 baseline is 3; the description still adds semantic value by explaining that after_rev is the panel.rev from a prior read and that wait_seconds is the mechanism for hearing a person's press, and by clarifying that omitting conversation_id targets the conversation most recently opened in the browser. This goes modestly beyond the schema text.

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 gives a concrete verb+resource ('Reads the panel: every tab, which one is in front, and every answered question in picks') after defining what the panel is, so an agent knows exactly what it retrieves. It does not explicitly differentiate itself from siblings like panel_ask, panel_update, or panel_close, so it stops short of a 5.

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?

It clearly explains the long-poll pattern: passing after_rev plus wait_seconds makes the call wait until something changes, framed as 'the way to hear the person's press.' That is real usage guidance for the polling case, though it never says when to use panel_ask/panel_open/panel_update instead, nor when a plain one-shot read is preferable to waiting.

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