discard_changes

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

Annotations declare readOnlyHint=false and destructiveHint=false, so the agent already knows this writes to staging without touching live state; 'without applying them' reinforces that scope. However, nothing is said about whether discarding is recoverable, whether it can be undone, or what happens to the pending operation records.

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?

A single front-loaded sentence that states action, target, and the key constraint with zero filler. Nothing could be removed without losing 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?

With one optional parameter fully documented, an output schema present, and annotations covering the safety profile, the remaining burden on the description is small. The only meaningful gap is reversibility/undo guidance for a discard operation.

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 'which' parameter is fully documented, including the 'all'/'last'/op-id forms and a cross-reference to preview_changes. The description adds no parameter meaning 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?

The description gives a specific verb ('drop') and resource ('staged changes') plus a scope qualifier ('without applying them'), which implicitly separates it from apply_changes. It doesn't name siblings, but the contrast with the apply step is inferable.

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?

Use is implied by the staging workflow: reject pending changes rather than commit them. It never states when to prefer this over preview_changes or apply_changes, nor any prerequisites (e.g., that changes must first be staged).

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