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

Without relying on the annotations (readOnlyHint=false, destructiveHint=true), it discloses that an agent is created, that a topic only finds content appearing after start, the credit cost of preview (1 credit), the pending_baseline status on a preset's first read, and the chat-mode deviation where nothing is created and a draft_id is returned instead. That is substantial behavior an agent could not infer from structured fields.

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?

Purpose and mode selection are front-loaded, and most sentences carry distinct information. The preview sentence is long and parentheses-heavy, packing three concepts into one clause chain, so it reads as a run-on even though nothing is pure filler.

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 creation tool with no output schema, it covers return values ('Returns the monitor and the agent'), the mutually exclusive input requirement, billing implications, and the chat-surface variant. An agent has what it needs to call this correctly in either surface.

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 schema carries most parameter documentation; the description still adds the exclusivity rule between url and query (the schema marks zero required params), plus the preview/preview_key chaining and the fact that the same preview_key can be reused when starting the watch. Genuinely additive but not exhaustive on the remaining params such as name or frequency.

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') plus the two modes (page URL vs topic query) and what it creates downstream (a Cloud Agent). It explicitly names the sibling it is not (draft_cloud_agent) and the exact user phrasings it serves, so it is distinguishable without opening any schema.

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 explicit routing ('Use it, not draft_cloud_agent, for tell me when <page> changes'), an explicit constraint on arguments ('Pass exactly one of url or query'), and a clear when-to-use for the preview mode including the multi-call follow-up with preview_key. Exclusions and alternatives are both present.

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