Clear handoff

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

The destructiveHint annotation already flags this as a write/destructive operation, and the description adds real value beyond it: it names exactly what is removed (the saved checkpoint) and the confirm=true guard that must be satisfied. It does not state reversibility or whether the checkpoint can be recovered.

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?

One sentence plus a short clause, with the destructive action front-loaded and the precondition attached immediately after. Nothing is wasted.

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 two-parameter destructive tool with annotations covering the safety profile and no output schema, the description supplies the key missing piece (confirm=true). It omits recovery/rollback behavior, which would be the only remaining gap.

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 50% (projectPath is documented, confirm has no schema description), so the description compensates by explaining that confirm must be true. The purpose of the confirmation gate is implied rather than spelled out, but the added meaning exceeds the schema alone.

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 the saved checkpoint for a project'), which is clearly distinguishable from save_handoff/update_handoff/get_handoff siblings by the destructive verb. It stops short of explicitly naming alternatives, so it is clear but not maximally differentiated.

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 usage context ('after the task is done') and a hard precondition ('Requires confirm=true'). It does not name when NOT to use it or point to an alternative tool, so it falls just short of full routing guidance.

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