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

Beyond the readOnlyHint/openWorldHint annotations, the description discloses three things the agent cannot otherwise know: that the source is CertSpotter rather than the name-implied crt.sh, that the data reflects issuance history rather than live state, and the exact billing model ($0.002 USDC per successful call via x402, failed calls free). The cost-per-successful-call disclosure is especially valuable for a paid tool and prevents surprise spending.

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?

It is front-loaded with the payload (what records and fields you get), then layers scope caveat, source caveat, and pricing. Every clause carries information an agent would otherwise have to discover at runtime; there is no filler or restated title.

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?

An output schema exists, so return values needn't be enumerated, and the annotations already declare the read-only/open-world profile. The description covers the remaining gaps an agent cares about — data source fidelity, issued-vs-live semantics, and cost — but omits any mention of result counts, pagination or how the 1-50 limit affects coverage, which would matter for an agent planning a broad enumeration.

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 both parameters (domain, limit) are already fully documented with examples and ranges. The description adds no syntax or format detail beyond the schema, which is acceptable at the baseline when the schema carries the load — but it earns no credit above that baseline.

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 names the specific resource (certificate transparency records for a domain) and the concrete data returned (certificate id, validity dates, revocation flag, DNS names including subdomains). It also states what the tool is not ('Shows issued certificates only, not live TLS configuration'), which lets an agent distinguish it from any TLS-configuration or recon tool 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?

The scope exclusion ('issued certificates only, not live TLS configuration') gives the agent a clear rule for when this tool is the wrong choice, and the data-source note tells it what index it is actually querying. What's missing is an explicit positive trigger such as 'use when you need to enumerate subdomains or certificate history for a domain' — the when-to-use is inferred from the returned fields rather than stated.

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