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

With only readOnlyHint=false declared, the description carries most of the burden and does so well: it says a Cloud Agent is created, describes the preview/preview_key credit flow, notes pending_baseline, and explains the cost and draft-confirmation behavior in chat. It omits any rate limits or plan gating beyond the frequency enum notes.

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 core purpose and routing are front-loaded, but the second half is a dense run-on covering preview semantics, credits, preview_key reuse, return values, status, and chat-card behavior. It is information-rich but packed into long sentences that are hard to scan.

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 tool with no output schema, the description covers the critical decision logic and behaviors (preview flow, credit costs, chat-draft behavior, topic timing). It leaves return-value detail unstated, which matters given no output schema, but overall an agent has what it needs to invoke correctly.

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 already high, but the description adds cross-parameter constraints the schema cannot express: exactly one of url/query, the domains restriction to topics, and how preview_key is reused across preview and watch. It adds meaning beyond the per-field descriptions.

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?

States a specific verb and resource ('Start watching the web') and distinguishes two modes (url page watch vs query topic watch) with clear scope. It explicitly contrasts itself against the sibling draft_cloud_agent by naming the exact user phrasings it owns ('tell me when <page> changes', 'let me know about <topic>').

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?

Gives concrete when-to-use guidance and an explicit alternative to avoid ('Use it, not draft_cloud_agent'). It also resolves the url-vs-query decision ('Pass exactly one of url or query') and explains a real caveat for topics ('a topic finds only what appears after it starts').

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