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

Annotations already flag destructiveHint=true and readOnlyHint=false, but the description adds genuinely non-obvious behavior: start/restart block until the process settles and return the reached state plus console output, and ok:true only signals acceptance of the signal rather than a healthy app. That is exactly the kind of operational nuance annotations cannot carry.

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?

Front-loaded with the signal vocabulary, then the blocking/return behavior, then the ok:true caveat — a sensible ordering with little waste. The parenthetical signal list slightly duplicates the enum, and the second sentence is dense, but nothing is filler.

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 mutation tool with no output schema, the description does the important work of describing the return payload (settled state, console output, recommended action). It omits edge behavior such as what happens when waitSeconds times out or when starting an already-running process.

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% (only waitSeconds is documented), so the description should compensate more. It does mirror the action enum in prose, but never explains what 'id' identifies or the practical difference between 'stop' and 'kill', leaving two of three parameters thin.

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 operation set ('Send a power signal (start / stop / restart / kill)') on a deployment, which cleanly separates it from sibling process-interaction tools like deployments_shell or deployments_command. An agent can tell what this does without opening the 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?

Usage is implied by the enumerated signals, and there is strong guidance on how to read the result ('Never announce that something works on ok:true alone'). However, there is no explicit when-to-use/when-not guidance relative to siblings (e.g., stop vs kill, or using deployments_shell for inspection), leaving the agent to infer selection criteria.

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