create_instance

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, and openWorldHint=true, so the safety profile is covered. Beyond that the description adds almost nothing behavioral: it does not mention that the chosen `period` commits to a 1/12/24-month billing contract, that the call provisions a billable resource, or whether retrying creates duplicates (relevant given idempotentHint=false). The one addition, a product/disk-size table, is selection data rather than behavior.

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?

The first sentence is duplicated almost verbatim by the second, and raw HTML <table> markup is pasted into the description. Worst of all it is cut off mid-cell ("<td>400 GB SSD</td><tr><td>V157</td>..."), so space is consumed without delivering the complete information it starts to.

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 heavy creation tool with a nested body object, ~12 properties, and no output schema, so the description should carry more weight. Key omissions remain: what the response contains (instance id? status?), whether provisioning is asynchronous, and the billing/permission implications. The product table partially compensates for productId, but nowhere near enough for the overall complexity.

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 every parameter, making 3 the baseline. The product table does add meaning the schema lacks for productId (which is described only as "Default is V153") by mapping V153–V157 to Cloud VPS tiers and disk sizes. However the table is truncated mid-row, so it stops short of being a reliable reference.

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 names a specific verb and resource ("Create a new instance") and includes the exact endpoint POST /v1/compute/instances, plus account scoping ("for your account"). It is clearly distinguishable from siblings like retrieve_instance, patch_instance, or upgrade_instance, though it does not state those distinctions 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?

There is no guidance on when to use this tool versus reinstall_instance, upgrade_instance, or create_object_storage, nor any stated prerequisites (e.g. that sshKeys/rootPassword reference pre-existing secretIds from Secrets Management). The embedded product table implies product selection but never says how to choose a product or what happens after creation.

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