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

With no annotations, the description carries the full burden and does well: it discloses the method ('rule-based from one live fetch plus DNS'), the cost ($0.006 USDC via x402 on Base or Solana), and the payment/auth model. It does not cover rate limits or timeout/failure behavior beyond the schema's 400 note, which keeps it from a 5.

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?

Telegraphic and front-loaded: use-case first, then input, then output, then method, cross-reference, example, and price. Every clause carries distinct information with no filler.

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?

There is no output schema, and the description fully compensates by enumerating the return structure (score, grade, per-category scores, findings fields, top fixes). Combined with cost and method disclosure, an agent has everything needed to decide and invoke correctly.

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 coverage is 100% and the single parameter is documented in both places, so the baseline is 3. The description adds value with an explicit format example ('?url=stripe.com') and the 'url or bare domain' restatement, clarifying accepted input shape beyond 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?

States a specific verb and resource ('grade a website and say what to fix') and enumerates the exact outputs (score 0-100, grade A-F, per-category scores, findings, top fixes). It also distinguishes itself from the raw-data sibling endpoint by pointing to /v1/web/site-profile, so an agent can tell it apart from site_profile or web_metadata.

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?

'Use when an agent must grade a website and say what to fix' gives a clear triggering condition, and the /v1/web/site-profile pointer tells the agent where to go for raw data instead. It lacks explicit when-not-to-use framing, so it sits just below the top.

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