Dry run

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

Beyond the readOnlyHint and destructiveHint annotations, the description explicitly states 'Spends nothing,' explains that it exactly mirrors create_instance, and describes the JSON return shape including next_tool and next_args. This gives the agent a concrete model of the tool's side-effect-free 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 description is two sentences with no filler. It front-loads the core behavior, then gives the key cost safety detail, then summarizes the return contract.

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?

The description covers the essential behavior, return shape, and safety profile, especially with strong annotations and an output schema present. The remaining gap is parameter semantics, but the analogy to create_instance plus the existing schema makes the tool reasonably actionable.

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 only 20%, and the description does not compensate by explaining template, idle_minutes, work_minutes, or teardown_minutes. It only says 'with these arguments,' which links parameters to create_instance but leaves their individual meaning and requirements under-specified.

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 clearly identifies the tool as a dry-run that replicates create_instance behavior, including teardown deadline and worst-case bill. It distinguishes itself from create_instance by stressing that it spends nothing, so an agent immediately knows what this tool is for.

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 references create_instance as the real operation being previewed and emphasizes 'Spends nothing,' which clearly implies using this before committing to create_instance. It does not explicitly list when not to use it or alternative conditions, but the context is clear enough.

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