iaas_update_machine

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

Goes well beyond the annotations: it warns that any existing tag not included in the patch body is silently unassigned, and that unsupported MachineSpecification fields are silently ignored. This is precisely the non-obvious side effect an agent needs before calling a mutation. It still says nothing about permissions or how the change is observed afterward.

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?

Opening line is duplicated verbatim ('Update machine. Update machine.'), which wastes the most prominent position. The rest is dense and useful, and the critical tag-loss warning is placed mid-sentence with a run-on '!All' artifact that hurts readability.

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?

No output schema exists, so the description carries the burden of consequence disclosure; it does that well for the tag replacement behavior and the ignored-fields behavior. Missing only auth/permission requirements and whether the response is synchronous, but for a PATCH with rich schema coverage this is close to complete.

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 schema already documents id, body, tags, bootConfig, description and customProperties. The description confirms which body fields are actually honoured, which adds a little meaning, but no format, merge-semantics or default details beyond the schema. Baseline 3 applies.

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 (update a machine) and immediately narrows scope to description, tags, customProperties and bootConfig. That scope restriction distinguishes it from siblings like iaas_resize_machine, iaas_power_on_machine or iaas_patch_machine_network_interface, though none are named explicitly.

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 tells the agent what is in-scope for this PATCH and that other fields are ignored, which implies other tools exist for those changes. But it never names an alternative (e.g. resize/power tools) or states prerequisites, so routing is left to inference.

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