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

With no annotations, the description carries the full burden and does it well: it discloses confirm:true requirements for a concrete list of destructive actions, that login key 'main' is stored but omitted from responses, that SQL export/import returns a phpMyAdmin link rather than a dump, and that large/binary files return a public URL instead of bytes. Remaining gaps (rate limits, per-action side effects) are minor against how much non-obvious behavior is already surfaced.

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?

Dense and telegraphic, but nearly every clause carries a distinct constraint (path rules, download link domain, MySQL prefixing, confirm list) rather than filler. Front-loading the scope and sibling exclusions before the caveat pile-up is the right structure; the fragment style is terse but hard to scan.

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 58-parameter, 95-action tool with no annotations and no output schema, the description covers setup order, path semantics, response quirks, and destructive-action gating, and points to get_guide for the rest. Given the complexity, it is complete enough to call safely, though per-action return behavior is necessarily deferred.

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 100% and the schema is unusually detailed, so the baseline is 3. The description's parameter notes ('FTP create uses type=ftp', 'Cron delete uses select0', path-prefix rules) largely restate what the schema already encodes in select0/cron_id/name descriptions.

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 states a specific domain (server scripts environment on the selected site) and explicitly rules out the three nearest siblings: modules_tool, files_tool, and ftp_tool. What holds it below 5 is the sheer breadth – 95 enum actions spanning uAPI, DirectAdmin env, MySQL, files, cron, FTP, Node/Python – so 'what it does' is clear as a category but diffuse as a single verb+resource.

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?

Provides real sequencing guidance ('call select_site first', 'Order: get_guide, status, ensure_ready') and predicates prerequisites on user approval. It does not give per-action when-to-use guidance for the 95 operations, but the get_guide pointer and the confirm gating cover the main routing decisions.

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