vcf_task

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

The description discloses key behaviors beyond the annotations: it reports status, failure subtask and reason, and explains the polling behavior controlled by wait_seconds. No contradictions with the readOnlyHint/idempotentHint 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?

The description is concise, front-loaded with the core purpose, and well-structured with a short intro, context, and Args list. Every sentence contributes value without redundancy.

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 provides sufficient context for a straightforward polling tool, including when to use it and what to expect on failure. It lacks explicit return format details (no output schema) and omits poll_interval, but overall covers the essential operational aspects.

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?

The description adds meaning for target (sddc or installer), task_id (returned by vcf_call), and wait_seconds (poll vs single check). However, it omits poll_interval entirely, leaving this parameter undocumented since schema coverage is 0%.

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 checks or waits on a long-running VCF task and reports status, including which subtask failed and why. It distinguishes itself from vcf_call by explaining that mutations return a task id, which this tool then monitors.

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 clear context: use this after a mutation returns a task id, and it can check once or poll until terminal. It does not explicitly name alternatives, but the context is sufficient and the default behavior (wait_seconds=0) is explained.

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