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

With no annotations present, the description carries the full burden and does well: it discloses that hard=true wipes data, that remove is not a permanent kill because the network re-spawns elsewhere, and that the owner key is required. It stops short of stating the return shape, whether restart interrupts live traffic, or any rate/latency characteristics.

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?

It is a tight, front-loaded block: each of the three actions gets one clause with the operative consequence, followed by scope and credential requirements. No sentence is filler and the destructive detail (hard wipes data) is placed right where the agent needs 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 seven-parameter mutation tool with no annotations and no output schema, the description covers the essentials: action semantics, destructiveness, persistence behavior, scope, and credential requirement. Gaps remain on return values and on why a payment key is needed alongside the owner key, but nothing critical to invoking 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 only 57%, so the description needs to compensate and largely does: it maps action to concrete effects, explains hard as a data-wipe flag, and clarifies that scope is either a single node or all nodes running the app. It adds little for the two private-key parameters beyond what the schema already says, leaving part of the coverage gap unaddressed.

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 states a specific verb set (restart/redeploy/remove) applied to a specific resource (app instances) and defines what each action actually does at the container and node level. It also differentiates itself from flux_cancel_app by explaining that remove leaves the registration in place and the network re-spawns the app, so an agent can tell it apart from the cancel sibling without opening either 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?

It gives explicit routing guidance for one key decision: use remove only if the registration should stay, and use flux_cancel_app instead 'to stop paying'. Scope usage is also stated (nodeIp for one node, global for every node). It does not spell out when to choose restart versus redeploy, leaving that choice implicit.

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