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

Annotations already declare destructiveHint=true, so the description's real added value is the detail of what gets destroyed (containers, volumes, and their data), the redeploy behavior of surviving services, the volume-pinned exception, and the approval interruption path. The exception clause is phrased vaguely enough ('except those whose Volume was there') to leave the reader guessing at the exact outcome, which keeps it out of 5 territory.

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 sentences, front-loaded with the destructive action, no filler. Minor awkwardness in 'Services still there stop' and 'except those whose Volume was there' costs it a point but the density-to-length ratio is good.

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, no-output-schema tool with five parameters, the description covers the consequences and the approval loop reasonably well but leaves the volume-loss authorization path and idempotency key unexplained. An agent could call it correctly in the happy path but would be under-informed on the risky branch.

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 20% (just the 'approval' parameter), so the description bears nearly the full burden — and it fails. The critical 'accept_volume_loss' parameter, which governs whether volume data loss is authorized, is never mentioned, nor are 'version' or 'request_key'. The description only obliquely hints at the approval mechanism.

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 ('Remove a server') plus the scope of collateral destruction ('delete its containers and volumes with their data'). It does not, however, distinguish itself from the closely-named siblings server_forget, server_clean, and server_drain, which an agent could easily confuse with this one.

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 conveys the operational consequence (services stop and redeploy elsewhere) and flags that human approval may be required, which implicitly tells the agent this is a heavyweight irreversible action. But it never says when to choose this over server_forget/server_clean/server_drain, and gives no prerequisites or when-not-to-use guidance.

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