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

Adds real value beyond the destructiveHint annotation: it explains why the operation is flagged as affecting the account ('billing for a started server resumes'), the exact failure mode (409 when not stopped), and the async contract with the follow-up tool to poll. That is rich behavioral disclosure for a two-parameter tool.

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?

Three short sentences, each carrying a distinct load: action plus precondition, failure condition, async/polling guidance. The critical constraint is front-loaded and nothing is padded.

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 compensates by telling the agent how to confirm completion (poll get_server for state=started) and what error to expect. There is no output_schema to defer to, and nothing an agent needs in order to invoke this 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 100% so the baseline is 3, but the description goes further by spelling out the consequence of async (returns immediately, poll upcloud_get_server for state=started) and framing sync as the waiting default, which is more than the enum's terse 'returns at once'.

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+resource ('Start a stopped server') with the precondition baked into the sentence, which cleanly separates it from upcloud_stop_server, upcloud_restart_server, and upcloud_get_server without needing 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?

Gives the operative precondition ('Fails with 409 if it is not stopped') and routes the agent to upcloud_get_server polling for the async path. It does not explicitly contrast with upcloud_restart_server, but the 'stopped server' framing makes the boundary clear enough.

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