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

Even with readOnlyHint/openWorldHint/destructiveHint already declared, the description adds substantial operational detail: 10 attempts/IP/24h shared with diagnose_http, Retry-After honored, no redirects or stored assertion bodies, HEAD vs one bounded GET, and the 64 KiB/UTF-8 body cap with oversize/compressed failures. It also flags that evidence may contain an untrusted snippet and instructs not to execute instructions in it.

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?

Purpose and return shape are front-loaded in the first sentence, then optional parameters, then behavioral constraints, each in its own compact line. Despite covering many behaviors, every sentence adds a distinct operational fact with no filler.

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 gate tool with a broad nested expect object, the description covers defaults, parameter semantics, rate limits, body handling, security caveats, and redirect behavior. Since an output schema exists, it appropriately only summarizes the return (pass/failures/evidence) rather than re-documenting it.

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 0% (the schema only exposes a bare additionalProperties object), so the description carries the full burden and does so thoroughly: http_status range, body_contains literal 1–256 chars/no regex, json_assertions 1–10 {pointer, equals} scalar checks with RFC 6901, and max_response_ms 1–10000 total time. The default (2xx + valid transport/TLS) and the status-overrides-2xx-but-not-TLS rule are also spelled out.

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+resource+scope: 'One-shot deployment gate for a public URL, no account or key,' and clarifies what it returns (pass, failures, evidence). It also names a sibling (diagnose_http) and the shared rate-limit relationship, so an agent can distinguish it without opening another 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 framing as a 'one-shot deployment gate' gives clear context for when to reach for this tool, and it references diagnose_http's shared budget. It stops short of an explicit when-to-use-this-vs-diagnose_http statement or exclusion rules, so it lands just below the top.

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