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

The annotations only cover safety profile (destructiveHint=false, idempotentHint=true), but the description adds the critical non-obvious behavior that a stopped server is still billed at full hourly rate because the GPU stays reserved. It also discloses the required permission scope (servers:stop) and account prerequisites.

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 action and its state effect, then the cost warning, then the alternatives, then permissions. Every clause carries distinct information with no 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 single-parameter mutation tool with no output schema, the description covers effect on data, billing consequences, alternatives, permission scope, and account requirements. Nothing material is left for the agent to guess.

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 100% and the single serverId parameter is already documented with its source (gpucloud_list_servers). The description adds no additional syntax, format, or constraint detail beyond the schema, so the baseline 3 applies.

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 resource ('Stops (shuts down) a server') and immediately clarifies the effect on state ('Disk and data are kept'), which separates it from delete and hibernate. An agent can identify the operation 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?

Explicitly names both alternatives and the conditions selecting them: use gpucloud_hibernate_server to pay much less, delete the server to stop paying entirely. This is textbook when/when-not/alternative routing.

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