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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is partly covered. The description adds genuinely useful context beyond them: cost ($0.05 USDC on Base), a possible shared trial, the privacy guarantee that no target payment or request bodies are stored, and explicit non-guarantees. However, the schema permits POST while readOnlyHint=true, and the description never reconciles that — an agent could reasonably wonder whether the scanner sends a mutating request.

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 decision-critical fact (alias, use listing_guard instead), which is the right ordering. It runs long, and the 'same operation, not two independent checks' point is restated across two clauses, but every remaining sentence (checks, return values, limits, price) carries information an agent needs.

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 2-parameter tool with no output schema and only two hints, the description covers return values (riskScore, flagged spans, rewrite suggestions), cost, privacy, and scope limits. The only real gap is method-selection semantics, which the schema does not supply either.

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 0%, so the description must carry the params, and it only partially does: 'Public HTTPS only' meaningfully constrains the url parameter's accepted form. The method enum (GET/HEAD/POST) is never explained — no guidance on which method to choose or why POST is supported for a read-only scan.

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+resource (a compatibility alias of listing_guard) and immediately clarifies the relationship: 'these are the same operation, not two independent checks.' The second sentence enumerates the actual checks performed (CDP technical validation, heuristic metadata screen for instructions, embedded URLs, tool calls, invisible Unicode, long fields, outlier prices), so an agent knows exactly what it gets and how it differs from siblings.

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?

Explicitly routes the agent: 'Prefer listing_guard for a new detailed metadata check' while explaining that check_listing exists only for existing clients. It also names the exclusion boundary ('Not Coinbase policy certification or guaranteed detection') and the operational precondition ('Public HTTPS only'), leaving nothing to inference about when to pick this over listing_guard.

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