instance_start

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

The description says that if the instance is already started, nothing will happen, which implies idempotent behavior on repeated start calls. This conflicts with the annotation idempotentHint=false, creating contradictory expectations for the agent.

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 description is short and front-loads the action and endpoint, followed by useful behavioral notes. It is slightly repetitive with 'compute instance / resource' and includes the endpoint path inline, but there is no major waste.

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 simple start action with complete schema coverage and annotations covering safety traits, the description covers the main behavior and status-check guidance. However, it does not state what a successful response contains, and the idempotency contradiction leaves the behavioral contract unclear.

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 parameter meaning is already provided by the schema. The description only restates that the instance is identified by id and adds no syntax, constraints, or format details beyond the schema.

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 uses a specific verb and resource: start a compute instance/resource identified by id. It also includes the concrete endpoint, leaving no ambiguity about the operation.

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?

It explains the power-on use case and says an already-started instance results in no action, and it points to retrieving instance information to check status. It does not explicitly distinguish when to use instance_restart, instance_stop, or instance_shutdown instead.

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