aws_run_instances

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

With no annotations provided, the description carries the full burden. It discloses cost ('billing starts immediately') and return format ('Returns JSON with the new instance IDs'). However, it lacks details on other behavioral aspects such as required IAM permissions, potential failure modes, or that instances may take time to become available. The safe guard mode hint is useful but not fully transparent.

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 four sentences long, front-loaded with the core purpose, then cost, usage context, and return format. It is concise and every sentence adds value. However, it could be slightly more streamlined by removing the 'Returns JSON' sentence if output schema were present, but since there's no output schema, it's appropriate.

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?

Given the tool's complexity (launching instances with 8 parameters, cost implications), the description adequately covers the critical points: purpose, cost, guard mode requirement, user confirmation step, and return type. It lacks details on error handling or post-launch behavior, but the schema is rich and the description provides sufficient context for safe usage.

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%, meaning each parameter already has a description in the input schema. The tool description adds minimal additional semantics beyond listing a few parameters to summarize (AMI, instance type, region, count). It does not explain parameter interdependencies or constraints beyond what the schema provides.

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 states the tool launches new AWS EC2 instances, with a specific verb ('launch') and resource ('EC2 instances'). It distinguishes from sibling tools like aws_start_instance (starts existing) and aws_terminate_instance by noting it's a creation operation that incurs costs immediately.

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 provides explicit guidelines: it is 'reserved for dangerous guard mode' and requires summarizing AMI, instance type, region, count, and confirming with the user before calling. However, it does not explicitly state when not to use it or suggest alternative tools, such as using aws_list_amis or aws_list_instance_types for exploration.

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