What is running

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

Annotations already cover read-only, non-destructive, open-world behavior. The description adds meaningful behavior beyond that: it flags instances lacking a teardown entry and reveals the return envelope includes next_tool and next_args, implying possible follow-up routing. This is useful context not present in annotations.

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?

Three tight sentences: the first defines scope and data, the second adds the flagging behavior, the third documents the return envelope. No filler or redundancy; all content earns its place.

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 parameterless read-only listing tool with an output schema and safety annotations, the description fully equips an agent to select and invoke it. It covers scope, included fields, special flagging, and the response shape, with no obvious missing guidance.

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?

There are zero parameters, so the schema carries no burden. The description correctly focuses on what the tool returns rather than parameters, matching the baseline for a parameterless tool.

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 identifies the resource ('every instance on the account'), the scope ('account'), and the specific data included (cost per hour, total spend, scheduled teardown). It clearly differentiates from siblings like get_instance (single instance) and list_templates/list_gpus (different resources).

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 makes the tool's purpose obvious, so an agent can infer when to call it for account-wide instance inventory. However, it does not explicitly state when to prefer this over get_instance or how it relates to the many lifecycle sibling tools, leaving the routing partly to inference.

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