combell_linux_hostings_subsites_create

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

Annotations already declare readOnlyHint=false, idempotentHint=false, and destructiveHint=false, so the mutation profile is established. The description adds value beyond annotations by disclosing that the folder must pre-exist (this operation does not create paths) and that Combell defaults to '/subsites/<subsite domain>' when path is omitted. It does not disclose return value, error behavior when the path is missing, or whether creation is synchronous or async — a notable gap given the sibling combell_provisioning_jobs_get suggests a job-based workflow.

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?

Two sentences, both of which earn their place. The first sentence front-loads the purpose (verb + resource + scope), and the second packs the critical precondition and default-path behavior without fluff, adjectives, or repetitive phrasing. No wasted words.

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 simple 3-parameter, fully schema-documented tool, the description covers the purpose and the main failure precondition (nonexistent path) well. However, with no output schema, the description is the only place that could disclose what the call returns — e.g., a provisioning job reference or a success status — and it is silent on this. It also does not address error behavior or idempotency consequences of re-creating the same subsite, leaving an agent partially uninformed about post-invocation expectations.

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%, so the baseline is 3. The description adds meaning beyond the schema by explaining the consequence of omitting the optional 'path' parameter ('when omitted Combell uses /subsites/<subsite domain>'), which the schema does not state. It also reinforces that 'path' must reference an existing folder, aligning with the schema's 'Existing folder on the hosting' wording. The other two parameters are fully covered by the schema with clear examples, so the description does not need to repeat them.

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 verb and resource: 'Create a subsite (an extra webite) on a Linux hosting.' The parenthetical '(an extra webite)' clarifies the Combell domain concept and scopes the operation to Linux hosting, distinguishing it from the many other create tools in the sibling list (e.g. combell_mysql_users_create, combell_mailboxes_create). However, it does not explicitly name its inverse sibling (combell_linux_hostings_subsites_delete), leaning on the naming convention rather than the description for sibling differentiation.

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 description provides one genuine usage precondition: 'The folder path must already exist on the server' — useful because it tells the agent not to expect the tool to create directories. It also explains the default path behavior when 'path' is omitted. However, it gives no guidance on when to use this tool versus alternatives, no exclusions, and no mention of the inverse delete operation, so routing to this tool vs. siblings relies on implication from the tool name.

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