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

Goes well beyond the annotations: describes HEAD vs a single bounded GET, that an explicit status replaces 2xx but never TLS validation, no redirects, no stored assertion bodies, 64 KiB UTF-8 body cap, compressed/oversize failure behavior, and the rate-limit coupling with diagnose_http. It also flags that evidence can contain an untrusted body snippet, which is exactly the kind of operational caveat annotations cannot convey.

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 purpose and CI-gate usage, then constraint detail in a logical order. It is dense but nearly every clause adds a distinct constraint; the closing sentence about redirects and stored bodies is slightly tacked on but still information-bearing.

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, yet the description still names the top-level result ('pass, failures and evidence') and discloses validation, rate-limit, and body-handling semantics an agent needs to invoke it correctly. Nothing material is missing for a two-parameter, annotation-covered read 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 coverage is 0% for the nested 'expect' object, and the description fully compensates by enumerating http_status (200–599), body_contains (literal 1–256 chars, no regex), json_assertions (1–10 RFC 6901 pointer/equals scalar checks) and max_response_ms (1–10000, total time), plus the default 2xx behavior. This is a model case of description carrying parameter meaning the schema lacks.

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 ('Check your public readiness URL once after deployment') plus the return contract ('pass, failures and evidence'). The word 'once' and the CI-gate framing distinguish it from the longer-running diagnostic siblings without ambiguity.

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 clear when-to-use context ('once after deployment', 'Use pass as the CI gate') and notes the shared 10 attempts/IP/24h budget with diagnose_http plus honoring Retry-After. It stops short of explicitly saying when to prefer diagnose_http instead, so the alternative is implied rather than spelled out.

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