nido_vm

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

No annotations are provided, so the description bears the full behavioral burden, and it discloses almost none. It never says that delete and prune are destructive or irreversible, what prune removes, whether delete frees disk, or whether start/stop are idempotent. The only real disclosure is the inspection-vs-mutation routing hint, which is useful but far short of what a twelve-action mutation surface requires.

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 sentences, front-loaded with purpose, then actions, then routing preference, with no filler. The twelve-action enumeration largely restates the schema's action enum, which is mild redundancy, but it does frame the tool's scope before the fallback instruction.

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 god-tool spanning twelve actions and twenty parameters with no annotations and no output schema, the description omits which parameters each action needs, what create returns, and any safety profile for the destructive actions. The resource-preference sentence is good, but it does not compensate for the missing per-action contract.

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 20 parameters and only 55% schema description coverage, roughly nine fields (gui, vcpus, memory_mb, ssh_port, ssh_user, vnc_port, cmdline, accelerators, plus partially name) have no documented meaning anywhere. The description adds no per-action parameter mapping, so an agent cannot tell from it that mapping belongs to port_forward or that user_data only applies to create.

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 ('Operate the VM fleet') and enumerates the twelve supported actions, which lets an agent match its intent to a named operation. It does not explicitly distinguish itself from siblings like nido_template or nido_image, even though the create-related parameters (image, template) overlap with them.

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 routes the agent: prefer the nido://fleet/vms and nido://vm/{name} resources for inspection when the client supports resources, and use this tool for mutations or as a universal fallback. What is missing is any guidance on choosing between actions in ambiguous cases, and no when-not conditions for destructive actions such as delete or prune.

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