Watch it come up

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

Beyond the readOnlyHint and destructiveHint annotations, the description discloses the polling timeout, the exact phase vocabulary, the need to call repeatedly, and the response envelope including next_tool and next_args. This gives the agent a strong behavioral model of the tool.

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 front-loaded sentences with no filler: the polling behavior, phases, repeat guidance, boot-time hint, and return format each earn their place. The structure makes the key call pattern immediately visible.

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 an output schema present and annotations covering safety, the description supplies the essential operational context: polling duration, phase list, repeated calls, and the JSON envelope. The unexplained template parameter is the only notable completeness gap.

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 33%, yet the description adds no parameter-specific details. It only indirectly reinforces max_seconds via 'up to 45 seconds' and leaves instance_id and template unexplained, which is a real gap for correct invocation.

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 action: polls for up to 45 seconds and returns the instance phase. It lists the possible phase values, making the tool's scope evident. It does not explicitly differentiate from sibling get_instance, but the polling/repeated-call behavior separates it enough for a strong score.

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 gives concrete usage guidance: 'Call repeatedly until online' and notes that weight downloads take most of the boot time. It does not explicitly state when to avoid this tool or name alternatives, but the usage context is clear.

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