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

Annotations cover the safety profile (readOnlyHint=true, openWorldHint=true), and the description adds substantial context beyond that: it discloses the exact number and kind of network calls made (one TLS handshake on 443 with SNI, one plain-http request, one https request), what the warning and failure thresholds are (under 30 days, expired, not-yet-valid), and that results are expressed as word-states with remediation. It stops short of saying whether results are cached or how long the check 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?

Front-loaded with the core action, which is good, but the enumeration of every measured attribute runs long and reads as a feature list rather than guidance. It is dense and information-rich but could be trimmed or bulleted without losing substance.

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 single-parameter read-only diagnostic with no output schema, the description does the heavy lifting of describing returned findings, state words, and remediation text. A brief note on response shape or ordering would make it complete, but an agent can call this correctly as written.

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 coverage is 100% and the schema already explains that a full address is accepted and only the host is used. The description reinforces this by emphasizing 'one public host' and 'Public addresses only', which meaningfully constrains input to publicly resolvable names — an added constraint beyond the schema's phrasing.

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 ('Checks one public host's SSL certificate') and then enumerates exactly what is measured: validity for the name, issuer, dates, chain, TLS version, HSTS, http-to-https redirect. Nothing in the sibling list does certificate inspection, so it is clearly distinguishable.

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 description scopes usage tightly ('one public host', 'Public addresses only') and implies the call is a one-shot diagnostic, but it never names an alternative tool or says when not to reach for it versus related site tools like mttr_site or mttr_rescan. Clear context, no explicit exclusions.

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