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

Annotations only give readOnlyHint=false and destructiveHint=false, so the description carries the real burden and delivers: a stopped server stops answering within minutes and requests no longer wake it, billing stops but disk is still charged, and stopping is non-destructive unlike destroy_compute. These are exactly the operational consequences an agent cannot infer from annotations.

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-loads the core action and resource in the first clause, then layers usage, alternatives, and timing/billing in tight sentences. Every sentence earns its place; nothing is redundant with the schema or annotations.

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 2-param, no-output-schema mutation tool, the definition covers parameter source, lifecycle timing, billing side effects, and how it differs from the sibling destroy/secret tools. No required context 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?

With 0% schema description coverage, the description compensates for machineId by stating its provenance (from lavela.project_overview), which is genuinely additive. The action values are fully enumerated in the schema, so the description need not restate them, but it adds nothing beyond machineId's source.

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 set (start/stop/restart) plus the exact resource (a server) and the identifying parameter (machineId from lavela.project_overview). It also draws explicit boundaries against set_compute_secret (which already restarts) and destroy_compute (which removes), so an agent can distinguish it from siblings 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 names when to use it ('restart a crashed server', 'start servers again after a top-up lifted a pause') and names alternatives with the conditions that select them (set_compute_secret for new secrets, destroy_compute for removal). This is a full when/when-not/alternative routing specification.

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