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

Beyond the destructive/idempotent annotations, the description discloses concrete consequences: scaling down stops running processes, scaling web to 0 takes the URL offline, a no-op when the count is unchanged, and the requirement to connect a Valet account. These are exactly the side effects an agent needs to warn about before a destructive call.

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 core action and per-kind rules are front-loaded, and every sentence carries a distinct constraint (range, safety confirmation, no-op, refusals). It is dense rather than padded, though it is long enough that a small amount of compression could tighten it.

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 destructive, non-read-only mutation with no output schema, the description covers the safety profile, prerequisites (Valet account), per-kind parameter rules, and refusal conditions. Nothing an agent needs to call it correctly is missing.

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 already 100%, so the baseline is 3. The description adds genuine value on top: the org-cap upper bound for app counts is not in the schema, it clarifies that process_type is app-only and omitted for agents, and that count is 0/1 for agents, reinforcing the enum-like meaning of kind.

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?

States a specific verb and resource ('Set how many processes of one type an app or agent runs') and immediately distinguishes the two target kinds (app vs agent) with different semantics. An agent can tell this apart from siblings like restart_service or destroy_service without opening a schema.

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?

Explicitly covers when to use it, the confirmation requirement before scaling down, the valid 0/1 range for agents vs the org-capped range for apps, and hard exclusions: websites are refused, and changing an agent's model is not offered here. This routes the agent away from unsupported actions rather than leaving them to inference.

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