upgrade_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. The description adds real value by disclosing the commercial consequence ('you can purchase add-ons'), but it omits whether add-ons can be removed, what happens on repeated calls, and any billing/approval prerequisite. It also names the wrong add-on set relative to the schema ('firewalling' vs. the schema's 'backup').

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?

Two short sentences plus the endpoint, with the purpose front-loaded and no filler. Minor redundancy between the header line and the explanatory sentence, but nothing wasted.

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 mutation tool with annotations present, no output schema, and a fully described nested body, the description covers the essentials of what the tool does. It falls short on consequences: cost/approval implications are only hinted at, reversibility is unstated, and the add-on list contradicts the schema, which is the one thing an agent most needs to get right here.

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 coverage is 100%, so parameters are already documented and baseline would be 3. However the description's statement that 'only firewalling and private network addon is allowed' conflicts with the schema, which exposes 'backup' and 'privateNetworking'; this actively misleads the agent about which add-on fields are legal, dropping it below the schema-only baseline.

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 ('Upgrading instance capabilities', POST /v1/compute/instances/{instanceId}/upgrade) and explains the tool buys add-ons, which is far more informative than the name alone. It does not distinguish itself from nearby siblings such as patch_instance or upgrade_object_storage, so an agent must infer the boundary.

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?

'In order to enhance your instance with additional features you can purchase add-ons' implies when to reach for this tool, but there are no explicit when-not conditions and no named alternative (e.g. use patch_instance for other instance attributes). Usage is inferable rather than stated.

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