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

Annotations only declare readOnlyHint and openWorldHint, so the description's additions are meaningful: exact price (0.02 USDC on Base via x402), a mandatory two-step payment handshake, and a rate limit of 3 free HTTP calls per day. A minor inconsistency remains between 'Input: {} (no input needed)' and the documented '?q=...' query parameter, which leaves the caller unsure whether a probe target must be supplied.

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 pricing/mechanism header is front-loaded, the core capability comes next, and the payment protocol and free-tier details follow in a logical order. The dated anecdote ('2026-11-04 07:34: caught 2 down and 4 broken servers...') and the '0.03 elsewhere for one' comparison are the only sentences that read as marketing rather than operational instruction.

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 paid, open-world read tool with no output schema, the description supplies what an agent actually needs to invoke it correctly: cost, the two-call payment protocol, the free tier, the endpoint shape, and the result categories. It stops short of describing pagination or the exact response payload, and the 'q' ambiguity slightly undercuts completeness.

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 the baseline is 3; the description's account of x_payment (signed payload returned from the first call) largely restates the schema's own text. It adds the workflow context for the parameter but leaves the 'q' parameter unexplained, even contradicting it with '{} (no input needed)'.

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 states a specific verb and resource with scope: 'Live-probes 100 MCP registry servers per call', and enumerates the outcome classes (up, auth-gated, broken, down, with each failing host). No sibling tool in the list performs liveness probing, and the description makes that unique function unmistakable.

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?

It gives operational sequencing ('call once without x_payment to get terms; call again with x_payment') and an implied use case via the anecdote about verifying a registry's 'unknown' liveness grade. However, it never states when to choose this over adjacent catalog/inspection siblings (store_catalog, list_service, store_samples) or what conditions make probing unnecessary.

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