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

Annotations already declare destructiveHint=true and idempotentHint=false, but the description goes further by spelling out the consequence ('running services restart and unsaved data in memory is lost') and the async operation model requiring polling via exoscale_get_operation. This adds real behavioral value beyond the structured hints.

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?

Four short clauses, front-loaded with the write semantics and risk, then the async pattern and endpoint. No sentence is padding.

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?

There is no output schema, and the description compensates precisely by stating that an operation is returned and how to poll it. Combined with the data-loss warning, an agent has everything needed to call and follow up on this tool correctly.

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 both the id pattern and the zone default ('the zone chosen at login') are already fully documented in the schema. The description adds no parameter-level detail, so the 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?

The description gives a specific verb (reboot) and resource (a running compute instance), and the 'running' qualifier distinguishes it from siblings like exoscale_start_instance and exoscale_stop_instance. It even names the HTTP endpoint, removing any 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 implies the instance must be running and directs the agent to poll the result with exoscale_get_operation, which is useful context. However, it never explicitly contrasts when to reboot versus stop/start, nor states prerequisites or exclusions, leaving the usage decision largely to inference.

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