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

With no annotations, the description carries the full burden and does substantial work: it discloses the billing policy (verified-only charging, unverified app not charged), the exact price (0.250 USDC per call), the payment rails (x402 on Base or Solana), and the verification prerequisite. What it omits is the scan's side effects on the target (outbound requests only?), rate limits, and how long a scan takes.

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 finding categories are front-loaded in one dense sentence, followed by fix availability, the prerequisite, the billing policy, and the price — each sentence adds new information. It is longer than typical but nearly every clause earns its place; the payment sentence could be trimmed slightly.

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?

No output schema exists, so the description must convey the return shape; it says each finding comes with a fix, which tells the agent the result is a list of issues plus remediations, though it does not describe the structure or severity fields. Combined with the cost and prerequisite disclosure, an agent has enough to call this correctly and anticipate being charged only if verified.

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?

A single required `url` parameter already has 100% schema description coverage, so the baseline is 3. The description adds only implicit context — that the URL must belong to an app whose ownership is proven via the verification token — and gives no format, scheme, or subdomain guidance beyond the schema's example.

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 ("Security check of a web app built with AI") and then enumerates the exact classes of findings: exposed secrets in the bundle, open Supabase tables, open Firebase, published .env/.git, missing headers. This is unmistakably different from every sibling (crypto_price, evm_balance, risk_token, etc.), so an agent can select it without opening the schema.

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?

Gives a concrete precondition for invocation: the app owner must publish a verification token first, obtained via POST /app-check/token. It does not name an alternative tool or state when a different check is more appropriate, but no sibling overlaps in purpose, so the missing exclusion costs little.

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