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

Beyond the annotations (readOnlyHint=false, destructiveHint=true, idempotentHint=false), the description discloses real behavior: conditional restart, the skippedRestart signal for static/PHP sites, waiting for the process to settle, and that the payload matches deployments.diagnose. The gap is that destructiveHint=true is never explained — nothing says what state is replaced or whether the applied changes are recoverable.

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 primary outcome, then routing, then behavior, then parameter overrides — a sensible order. The parenthetical about static/PHP sites is slightly dense but earns its place by explaining skippedRestart. No filler sentences.

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?

With no output schema, the description carries the return-value burden and does so by pointing at deployments.diagnose's payload and calling out skippedRestart. What remains missing is the destructive/permission context for a tool flagged destructiveHint=true, which matters given the mutation semantics.

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 67%, so the schema already documents restart and waitSeconds. The description reinforces restart semantics and usefully explains the runtime-decides default, but adds nothing about waitSeconds (defaults, limits) beyond what the schema states. Marginal value over structured fields, so baseline-plus.

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 opens with a specific verb+resource outcome ('Make edited files live and confirm they work, in ONE call') and explicitly names the composite of siblings it replaces (deployments.power + deployments.logs + deployments.check). An agent can distinguish it from deployments_diagnose, deployments_power, and deployments_logs without opening any 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 states the trigger condition ('Use this after writing files') and the alternatives it supersedes by name. It also gives conditional guidance on the restart parameter (force vs forbid vs omit to let the runtime decide), covering the main decision an agent faces.

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