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

Beyond the readOnly/destructive annotations, it discloses that status may reflect a running or failed import_site job, that write_site overwrites the header wholesale (a real blast-radius warning), and that the no-token path returns only public content and omits status. It doesn't cover failure modes or how large wikis are paginated, which keeps it short of a 5.

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 dense with no filler and leads with the return payload, but the final clause ('With `site` and no token, any live site's name, address and pages as it lists them, a wiki's being its articles outside hidden categories, without its status') is a run-on that is hard to parse on first read.

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 enumerating the returned fields, and annotations already carry the safety profile. The remaining gap is modest: the no-token mode's boundaries ('any live site', custom domains) are implied rather than nailed down.

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 interaction semantics the schema doesn't: supplying `site` without `token` yields the anonymous public view, and for wikis that view is limited to articles outside hidden categories with no status. That is genuine added meaning about how the two parameters combine.

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?

The description names the resource and enumerates exactly what is returned: name, theme, header, address, every page by path and title, job status, and domain. This is a specific verb+resource statement that an agent can distinguish from read_page, search_site, and get_stats without opening the 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?

It gives an explicit precondition ('Call before changing a site you did not just create') and names the sibling that mandates it ('write_site replaces the header whole, so change it from this one'). It also defines a second usage mode — `site` with no token for public, unauthenticated reading — so both invocation patterns have a stated when-to-use.

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