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

Annotations already declare readOnlyHint, openWorldHint, and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful behavior beyond that: weekly aggregation and a bounded ~6-month retention window. It does not disclose error behavior when both or neither of origin/url are given, nor that the underlying source is CrUX/public origin-level data with coverage limits.

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?

Two sentences, zero filler, and the scope/granularity constraint is front-loaded before the parameter rule. Nothing could be cut without losing information.

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?

Annotations cover safety and there is no output schema, so the description need not explain return values. Still, for a 4-parameter analytics tool with 25% schema coverage, it leaves form_factor entirely unexplained and gives no hint about data availability caveats (e.g. low-traffic URLs having sparse CrUX history).

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 only 25% (only "chart" is described), so the description must carry the load. It does clarify the origin/url mutual exclusivity that the schema leaves ambiguous (no required fields, no oneOf) – that is real added meaning. However, form_factor is undocumented in both places and the description never explains what origin vs url scope actually changes in the returned data.

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?

"Weekly Core Web Vitals history (up to ~6 months) for an origin or URL" names a specific resource (CWV time series), its granularity, and its scope. The word "history" implicitly separates it from the snapshot siblings cwv_get_origin and cwv_get_url, though those siblings are never named so the differentiation is inferential rather than explicit.

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?

"Give exactly one of origin or url" is a real precondition and prevents a common misuse, so there is more than nothing. But it says nothing about when to pick this over cwv_get_origin / cwv_get_url, nor when the ~6-month window makes this tool inappropriate versus a current-snapshot call.

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