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

With no annotations at all, the description carries the full disclosure burden, and it does well on several counts: deterministic execution, explicit non-capability (no composition/alignment judgment), output shape (score 0-100 plus findings with evidence and fix), and auth/cost ('FREE, no key required'). What it omits is whether the tool touches or persists anything — nothing states it is read-only and non-mutating — and there is no mention of rate limits or size constraints on the HTML input.

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 purpose is front-loaded in the first clause, followed by the check inventory, then the capability limit, then output/cost. Four dense sentences with no filler; even the long enumeration earns its place because each named check is a distinct thing the agent can expect in the findings.

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?

For a one-parameter analysis tool with no output schema, the description covers the missing pieces itself: what is checked, what comes back (score plus per-finding evidence and fix), what it cannot do, and that it is free and keyless. An agent could call this correctly on the first attempt with no further information.

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?

There is a single parameter with 100% schema description coverage ('the page's full HTML'), so the schema already does the work and baseline 3 applies. The description adds no detail on input expectations — no note on whether stylesheets or scripts must be inline, whether fragments are acceptable, or any size limit — so it neither compensates for nor undermines the schema.

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 gives a specific verb and resource ('critique a composed page') and enumerates exactly what is checked — AI-gradient tells, default typography, dead frames, contrast failures, repeated section grammar, motion-safety gaps, placeholder copy, slop grammar — so an agent knows precisely what class of analysis this is. It also carves out a boundary ('deterministic markup analysis, not visual review'), though it never names the adjacent sibling tools (audit_page, verify_complete, verify_repair), so differentiation from them is left to inference.

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?

'Before shipping' establishes the moment of use clearly, and 'it cannot judge composition or alignment' tells the agent when to reach for something else instead. The gap is that no sibling is named as the alternative for the visual/composition case, so the agent must guess which of audit_page or verify_complete covers that.

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