eng.manage_infrastructure

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

No annotations are provided, so the description carries full burden. It mentions 'query or modify' but does not disclose that the 'delete' action is destructive, nor does it discuss permissions, rate limits, or side effects. Only partially 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 a single sentence that efficiently states purpose and key capabilities. It is front-loaded with the main action and resource scope. No wasted words.

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?

With no output schema and 3 parameters including a destructive action, the description lacks details on return format, error handling, and prerequisites. It mentions viewable fields but does not cover all actions or behaviors, leaving gaps for an AI agent.

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% with basic descriptions. The description adds value by explaining what can be viewed (status, IPs, access configs) but does not clarify what each action (list, status, delete) returns or requires. Provides marginal extra meaning.

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 queries or modifies cloud infrastructure (EC2, RDS, S3) and mentions viewing status, IPs, and access configs. It distinguishes from sibling tools like eng.trigger_deployment, which handle deployments.

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?

No guidance on when to use this tool versus alternatives. For example, it does not note that provisioning or deployment should use eng.trigger_deployment, or that read-only queries might be preferred with eng.query_repos. Missing when-not and alternative context.

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