vm_improvements

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

With no annotations supplied, the description carries the full burden, and it does disclose real behavioral traits: no model call, no success inference, and no automatic activation — useful negative guarantees for a diagnostic tool. It does not say whether the optional save persists state, where, or with what side effects, so the mutation profile remains unclear.

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?

Two short sentences with the verb front-loaded and no filler, which is structurally sound. However, the density comes from unexplained jargon rather than precision, so brevity is achieved at the cost of comprehension.

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 diagnostic tool with no annotations, no output schema, and zero schema coverage, the description should explain what counters are read and what the diagnosis yields. It never says what the result contains or how it relates to the review/status siblings, leaving the agent unable to predict the outcome.

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 0%, so the description must compensate. It partially explains `save` ("Optionally save deduplicated pending ideas") but gives no meaning at all for `owner_thread_id`, leaving half the parameters undocumented in both schema and prose.

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?

A verb ("Diagnose") is present, but the objects are opaque compound jargon — "unused review/image comparison", "uncertain transport", "pending cleanup from counters" — that an agent cannot map to a concrete resource or operation. Nothing distinguishes this from siblings like vm_review or vm_status, which sound related.

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?

There is no when-to-use guidance and no named alternative among the 22 sibling vm_* tools. The only conditional hint is "Optionally save deduplicated pending ideas", which addresses a mode rather than selection between tools.

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