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

Annotations already declare readOnlyHint=true and openWorldHint=true, and the description adds genuine context beyond them: this is a polling endpoint whose terminal condition is status != running, errors surface a reason, and it requires vms.read scope. Return shape details and polling cadence/limits are not covered, so it is strong but not exhaustive.

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 clauses, front-loaded with the core behavior, then the polling contract, then the required scope. No filler sentences and no repetition of the title.

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 one-parameter polling tool with no output schema, the description should at least say where the action identifier comes from and roughly what fields (status, error message) come back. It gestures at status and error reason but leaves the input source and response shape underspecified.

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?

The single parameter 'action' has 0% schema description coverage, so the description carries the full burden, and it only indirectly hints at the domain with '(create, reinstall, power…)'. It never says the parameter is an integer action ID nor where to obtain one (list_vm_actions), leaving the agent to guess at the value's origin.

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 ('follows') and resource ('an asynchronous action'), with concrete examples of action kinds (create, reinstall, power). It does not name the closest sibling list_vm_actions, so the distinction between polling a single action and listing actions is left to inference, keeping it below a 5.

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?

'Poll until status leaves running' gives a concrete usage pattern rather than a generic verb, and 'on error it carries the reason' tells the agent what to expect on failure. It still gives no explicit routing such as 'use list_vm_actions to find the action ID' or when not to call it, so it stops short of a 5.

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