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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds pricing ('FREE during validation') and auth ('No key, credits, wallet') context that is useful, but does not explain the explicit shared output budget or the effect of maxChars beyond what the fragment already hints at.

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 description is short but fragments into disconnected facts ('Explicit shared output budget and scope', 'Supply your task in input') that read like marketing copy rather than a coherent front-loaded statement. Some sentences do not earn their place.

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 an output schema present, return-value explanation is not required, so the description need not describe output. However, for a nested-input diff tool with 0% schema coverage, the description omits important parameter guidance and only partially covers behavioral aspects like budget and scope.

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 description coverage is 0% for a nested object with four fields, so the description should compensate. It only repeatedly references 'input' without documenting beforeHtml, afterHtml, maxChars, or sourceUrl, leaving the schema to carry the field semantics. Baseline for poor coverage with some implicit context is 3.

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 ('return added and removed content blocks') and resource ('before/after HTML'), which is clear. It does not name or distinguish itself from siblings like page_delta_preview or commerce_feed_page_compare, so it lacks explicit sibling differentiation.

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?

'Avoid rereading unchanged text' implies when to use the tool (comparing page versions to save tokens), but there are no explicit when-not-to-use conditions or named alternatives. Usage is implied rather than stated.

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