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

Annotations only declare readOnlyHint and openWorldHint; the description adds substantial context beyond them: robots.txt is respected, nothing is stored, one real browser load is performed, and the call is paid ($0.02, x402). Cost and data-handling disclosures are exactly the kind of behavioral detail an agent needs before invoking.

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?

Front-loaded with the primary deliverable and dense but well-punctuated with semicolons rather than filler. It is on the long side and somewhat run-on, but nearly every clause conveys a distinct capability or constraint.

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 carries the return-value burden and does so thoroughly: it names the grade, the four scores, the issue-list-with-fix format, and each underlying check. An agent knows what it will receive and what the call costs.

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%, so url, device, and screenshot are already fully documented in the schema. The description echoes the optional screenshot and browser-load behavior but adds no format or constraints beyond what the schema provides, matching the baseline for high-coverage schemas.

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 and resource ('Full website audit in one call') and enumerates the exact scope: A-F grade, four dimension scores, and all issues with fixes. This clearly distinguishes it from narrower siblings like site_speed and site_metadata by emphasizing the comprehensive one-call coverage.

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?

Usage is implied through the 'full audit in one call' framing and the cost/mechanism note, but the description never explicitly says when to choose this over site_speed or site_metadata, nor does it state prerequisites or exclusions. Adequate but no routing guidance.

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