Corrie Site Check

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

Goes well beyond the annotations: it discloses refusal cases (private/internal/local, plain http, non-443 ports, user names) and the isError outcome, latency (1-10s), idempotency caveat ('same result unless the site changed'), statelessness ('nothing is stored'), and a pointer to corrie://docs/scoring for the scoring model. Annotations only cover safety hints, and the description adds substantive operational context on top.

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 a long description, but it is front-loaded (what it loads, what it returns) before examples, exclusions and limits. Nearly every sentence carries distinct, decision-relevant information, though the enumeration of headers and the examples section could be trimmed slightly.

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?

Output schema exists, so return-value explanation was not required, yet the description still maps the result shape (score, verdict, certificate issuer/expiry, findings with severity and fixes). Combined with the refusal behavior and timing, an agent has everything needed to call this correctly and interpret failures.

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%, so the baseline is 3, but the description adds meaning the schema does not: bare domain checks the homepage while including a path loads only that page instead. That is a genuine semantic addition beyond the documented parameter.

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 — loads a public website's homepage over HTTPS and reports its HTTPS/TLS/header posture. The scope is exact enough that an agent knows precisely what is and is not covered; no sibling tools exist to disambiguate from.

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?

Gives concrete trigger questions ('is example.com secure?', 'what headers is my site missing?', 'why does Chrome say my site is not secure?') and explicit exclusions (no logins, forms, port scans, crawling or vulnerability testing). It also spells out the refused input classes and that they surface as isError with a corrective message, so routing is unambiguous.

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