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

Goes well beyond the readOnlyHint/openWorldHint annotations by disclosing cost ($0.002 USDC per call via x402 in-call), the two token payment paths (kyapay-token header or argument), the no-charge-before-answer rule, the no-charge-on-failure policy, and the free 304 behavior when an ETag matches even after a newer read. Those are exactly the operational traits an agent must know before calling a paid tool.

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?

Every sentence carries real information (availability, payload, caching, pricing, failure policy), but the ordering is awkward: it leads with 'Not answering yet' before stating what the tool returns, and the ETag/304 point is restated in the schema. The rhetorical question mid-description interrupts the flow.

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 readOnlyHint/openWorldHint annotations, three fully documented parameters, and no output schema, the description carries the return-value burden and does list the payload fields (grade, score, stop findings, sign-in, tools, digest). It stops short of saying how the response is signed or what the envelope looks like, a minor gap for a 'signed fact' tool.

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 schema already explains the server identifier (registry name or URL), the kyapay-token fallback, and the if_none_match ETag semantics. The description reinforces the payment/ETag meaning but adds no syntax or format detail the schema lacks; baseline 3 applies.

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?

Once past the opening availability caveat, the description states a specific resource and payload: 'One signed fact from Agoranome's newest read of a server with a public report card: its grade and score, confirmed stop findings..., sign-in, the tools it lists and a digest of what a model reads of them.' An agent can tell this returns a point-in-time attestation of an MCP server rather than analytics or a ranking. It never names a sibling (e.g. buyer_check, rank_check) as the alternative, so differentiation is left implicit.

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?

The framing question 'Has this MCP server changed since my agent approved it?' gives a clear use case, and the description states availability boundaries (answers from 17 Nov 2026; a card opens two weeks after a server's first read). It does not point to any alternative tool for servers that lack a public card, leaving that inference to the agent.

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