sylve_vm_create

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

Annotations already declare the destructive, non-idempotent, non-read-only profile, and the description adds genuine value beyond that: it discloses auto-allocation of RID and VNC port (side effects the agent cannot see in the schema) and cloud-init YAML validation. It does not cover failure behavior, what a partial creation leaves behind, or whether dry_run still validates, which keeps it below 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?

Three short sentences, front-loaded with purpose and with zero filler; the auto-allocation and validation details earn their space. It is arguably too terse for a 45-parameter mutation tool, which is the only real structural weakness.

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?

This is a 45-param, nested-object, destructive, non-idempotent creation tool with no output schema and no required fields, yet the description never says which parameter combinations produce a valid request, what is returned (e.g., an RID), or what happens on partial failure. The complexity-to-description ratio is badly unbalanced; three sentences cannot cover it.

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?

With 45 parameters and only ~51% schema description coverage, the schema does roughly half the work and many fields (tpm, serial, cloud_init, qemu_guest_agent, pci_devices, rewrite_cloud_init_identity, wait_timeout) have no description at all. The description explains only a tiny slice — size-string parsing for memory/disk_size, automatic RID/VNC port allocation, and dry_run — leaving template-mode params and mode-exclusivity undocumented.

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+resource ("Provision a Bhyve VM") and names the two creation modes (from scratch or from a template), which separates it from the read/action siblings. It stops short of explicitly distinguishing itself from sylve_vm_template or sylve_vm_action, so the agent must infer that boundary from the name alone.

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?

There is no when-to-use / when-not-to-use guidance and no prerequisites (which params are needed for scratch vs template mode, which are mutually exclusive). The only usage signal is "Supports dry_run", which hints at a safe preview path but is not framed as guidance.

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