web_watch

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

Annotations only declare readOnlyHint=false and openWorldHint=true, so the description must add the interesting behavior – and it does: a no-op check costs one conditional request, watches persist across restarts but only run while the server is up, and a broken css_selector is relocated by fingerprint. It stops short of stating auth needs or what a change report looks like.

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 purpose in sentence one, then packs action semantics, cost, persistence limits and the alternative into three tight sentences with no 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?

With no output schema the description still conveys what list/check report and the cost model, and it covers persistence and the sibling alternative. Only the exact shape of a change report and any permission requirements are left unstated.

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 restates the interval_secs default and the action vocabulary rather than adding new syntax or format meaning beyond the schema's own descriptions, so it neither compensates for a gap nor adds much.

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 (watch) and resource (a page or one css_selector region of it) and immediately names the sibling it is not: web_diff for a single comparison. An agent can distinguish it from web_diff/web_snapshot 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?

Enumerates each action (add/list/check/remove) with its meaning, and explicitly routes the no-watch single-comparison case to web_diff. That is an explicit when-to-use plus an alternative, leaving little to inference.

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