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

Annotations already declare read-only/idempotent/closed-world, so the bar is lower, but the description still adds real context: data is read from the server, updatedAt means when Squish applied the build, and Squish (not the customer) patches shared servers. It stops short of describing failure behavior for a non-shared or unknown domain.

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 what is returned, then when to call, then exclusions. Dense and largely waste-free, though the quoted-query sentence and the patching-responsibility aside make it longer than strictly needed.

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?

With no output schema, the description compensates by naming the returned fields and their granularity. Coverage is nearly complete; the only gap is what the tool does or returns when the domain isn't a shared hosting site.

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?

Single required parameter with 100% schema description coverage, so the schema already carries the definition. The description adds only a mild constraint that the domain belongs to the customer's SHARED hosting site, with no format or normalization guidance.

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 ('Returns what one of the customer's SHARED hosting sites actually runs, read from the server') and enumerates the exact fields returned (PHP version to patch level, handler, build update date, installed builds, control panel, OS). This clearly separates it from siblings like detect_technology, get_my_site_health and diagnose_my_server.

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?

Explicitly prescribes invocation with 'CALL THIS for "what PHP version am I on", "am I patched for <CVE>", "is my server up to date"' and gives an explicit exclusion ('A Managed Cloud server is not covered here'). It also explains the domain/ownership model, so the agent knows who owns patching.

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