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

Annotations already declare readOnlyHint=true and idempotentHint=true, and the description adds meaningful context beyond them: scores are 'derived deterministically from the same checks as audit_page', no browser is launched, and the url argument is actively REJECTED (not silently ignored) on the hosted endpoint. This rejection behavior and determinism are genuinely additive and consistent with the idempotent hint.

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 front-loaded with a strong purpose statement, but the final two sentences repeat what was already stated in the third sentence: 'score_page url-capture is disabled on the hosted (remote) endpoint. Pass the page HTML via the "html" argument instead' restates 'Pass html directly; the url argument is REJECTED on this hosted (remote) endpoint.' The phrase 'hosted (remote) endpoint' also appears three times, making the description longer than necessary.

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 present, the description carries the burden of documenting return values, and it does so thoroughly: 7 category scores (0–10), overall 0–100 score, A–D grade, weakest category, and the three non-mechanical categories with tool guidance. Combined with the strong parameter schema and safety annotations, the tool is fully comprehensible; it only misses an example or more concrete detail on the guidance for brand/conversion/motion tools.

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 100% and each parameter (url, html, strict, containerMaxWidth) already has a detailed schema description including the hosted-endpoint rejection of url. The description adds emphasis by pointing to html as the correct input, but contributes little semantic information beyond what the schema already provides, so the baseline 3 is appropriate.

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?

The description opens with a specific, actionable statement: 'Score an HTML/CSS page across 7 design categories' with each category enumerated and its 0–10 rating scale stated. It clearly distinguishes from siblings by explicitly referencing audit_page ('same checks as audit_page') and noting it covers categories Raven does not mechanically assess, differentiating it from both the audit_* family and score_creative.

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?

The description gives explicit when-to-use guidance: use this tool for deterministic scoring 'no browser required' versus audit_page (which presumably renders). It names audit_page as the direct alternative, provides the hosted-vs-local usage split ('Pass html directly; the url argument is REJECTED on this hosted (remote) endpoint'), and even directs users toward other tools for brand/conversion/motion categories.

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