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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open world), and the description adds behavior they cannot: each place is read twice a few seconds apart, so the call is not instant, and the meaning of the 'steady: false' signal plus the guidance to pick a narrower place when content fluctuates. With no output schema, disclosing that return signal here is genuinely load-bearing.

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?

Three sentences, front-loaded with the core action, and none of them is filler. The final sentence is dense and slightly run-on with its parenthetical 'steady: false' explanation, which mildly hurts scanability but not comprehension.

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?

No output schema exists, and the description does explain the key return signal (steady) and the double-read mechanism behind it. It stops short of describing the overall response shape — e.g. how text is returned per selector — which leaves a small gap for a tool whose sole output is the payload.

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% and both parameters are documented there, so the description adds little param-level detail beyond implying multiple selectors are allowed. It does hint that selectors come from preview_page, which is useful workflow context but not syntax-level semantics. Baseline 3 applies.

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 — read what places on a page say right now — and immediately sets scope against watching ('without watching anything'), which cleanly separates it from watch_page and get_watch. An agent can tell exactly what this does without opening the 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?

Explicitly prescribes the workflow: use it to try selectors before watch_page or update_watch, instead of creating and ending a watch. That names the alternatives and the condition that selects this tool, plus an implicit when-not (continuous observation belongs to watch_page).

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