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

Annotations declare destructiveHint=true and non-idempotent, but the description adds the details annotations cannot express: data is permanently unrecoverable, calling without confirm refuses and does nothing, and the app restarts without the variable. This is exactly the behavioral context needed for an irreversible operation.

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?

Four short sentences, front-loaded with the destructive action and its effect, then the confirmation protocol, then the alternative. No redundant restatement of the schema.

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 an output schema present, return values need no explanation; the description covers irreversibility, the confirmation gate, the refusal path, and the downstream effect on the app's environment. Nothing an agent needs to call this safely 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% and the confirm parameter is already documented, so the baseline is 3. The description still adds behavioral meaning by explaining the consequence of omitting confirm (the call refuses and nothing happens), which the schema does not state.

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 ("Drop a project's managed Postgres database") plus the accompanying state change ("unset DATABASE_URL"). It also contrasts with the closest sibling, rotate_database_password, so the agent can distinguish the two without opening either 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 an explicit protocol: first reply that data is deleted and unrecoverable, ask for confirmation, stop, and only call with confirm: true after a yes. It also names the alternative for a different intent (replace a leaked DATABASE_URL → rotate_database_password), leaving nothing to inference.

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