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

Despite no annotations, the description fully carries transparency: 'Deterministic, no LLM' and 'every finding cites the exact matched HTML' assure reliability. It also details the output format (score 0-100, per-section tells, prescriptions) and hints at the underlying graph shared with recommend_patterns, adding behavioral context beyond any structured metadata.

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?

At about 70 words, the description is tightly packed with no filler. Each clause introduces a new fact: the audit criteria, determinism, output components, and follow-up tool calls. It is front-loaded with the core action and then provides necessary detail.

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 thoroughly explains return values (ai_shaped_score, per-section evidence, page-level tells, prescriptions) and even names the next tool calls to fetch/validate them. It also conveys the tool's read-only nature indirectly via 'Audit', though it never explicitly states that at least one of url/html must be provided; however, the schema's 'alternative to html' phrasing covers that implication.

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?

Both url and html have rich schema descriptions covering fetch constraints, size caps, timeouts, and one-page-per-call, so schema coverage is 100%. The tool description adds no parameter-specific meaning 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 'Audit an EXISTING page' — a specific verb and resource — and enumerates the exact patterns checked ('numbered steps, a centered hero...'), clearly distinguishing this from sibling creation tools like build_page/compose_page. The mention of 'any AI builder, any stack' broadens the resource scope without losing specificity.

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?

It establishes clear usage context: existing pages from any AI builder, plus 'FREE, no key required' signaling no authentication barrier. It implies use before redesign or replacement of sections, but does not explicitly name when not to use it or compare it to similar sibling tools like get_design_digest.

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