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

Goes beyond the annotations (which only flag destructiveHint/idempotentHint) by explaining irreversibility ('can no longer be restored afterwards'), the last-checkpoint guard, and a confirmation requirement. These are exactly the behavioral traits an agent needs before invoking a destructive mutation.

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 tight sentences, front-loaded with the action and risk before the guard and confirmation. No wasted words and every sentence carries distinct information.

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 single-param tool with no output schema, the description covers irreversibility, the deletion guard, and the confirmation protocol. Slightly richer context on what happens to dependent state (e.g., deployments referencing the checkpoint) would make it complete.

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?

Only one parameter, and the schema already documents it at 100% coverage including the source ('from list_checkpoints'). The description adds no parameter semantics beyond the schema, so 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 ('Delete one checkpoint') and scopes it to a project's version history, so it is distinguishable from restore_checkpoint and rename_checkpoint. It does not explicitly name those siblings, which keeps it just short of a 5.

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 a concrete precondition ('Confirm with the user first') and states the blocking edge case ('last remaining checkpoint cannot be deleted'). It lacks an explicit pointer to alternatives like archive_project or how to recover, but the usage context is clear.

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