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

Annotations already declare this a safe, idempotent, closed-world read, so the bar is lower. The description still adds real value by noting the diagnostic behavior of check=true and that the "needs attention" section is counts-only, but it omits that check=true is a heavier scan and doesn't clarify the odd const-true constraint.

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?

A single dense sentence front-loads the resource and then lists return contents with no filler. It reads as a run-on, with the check clause tacked on the end, but nothing is wasted.

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 described, and annotations cover the safety profile. Given a two-parameter read tool, the description supplies the payload overview and the check behavior — the only real gap is `site` format, which keeps this from being flawless but is minor in context.

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%, so the description carries the full burden. It gives partial meaning for `check` (checks pages and settings) but says nothing about the required `site` parameter — no expected format (subdomain, ID, or domain) — and never explains why `check` is constrained to the literal true rather than a boolean flag.

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 ("Reads a site's app") and enumerates the payload (on/off, sign-up, path, plans, user counts, lists with row counts), so an agent knows exactly what comes back. It does not differentiate itself from close siblings such as get_site, get_app_data, or check_site, and the embedded check semantics overlap with check_site.

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?

Usage is only implied: "check: true checks pages and settings" hints at when to enable the extra scan, but there is no statement of when to call this versus get_site, get_app_data, or check_site, and no prerequisites or exclusions. An agent must infer selection from the payload list.

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