Discard the change

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

Annotations already flag destructiveHint=true and readOnlyHint=false, so the safety profile is covered. The description still earns credit by specifying what actually happens beyond the annotation: all edits are reverted to the prior file state and the change is closed, not merely left open. It stops short of stating whether the discarded change is recoverable or what happens when no change is open.

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 sentence, front-loaded with the action verb, with no redundant restatement of the name or title. Every clause carries information: the scope (every edit), the mechanism (restore files), and the postcondition (close it).

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 zero-parameter mutation tool with full annotation coverage and no output schema, the definition covers effect and end state adequately. The remaining gap is edge-case behavior – no open change present, or whether the revert can be undone – which an agent might want before invoking a destructive 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?

The tool takes zero parameters, so there is no parameter meaning for the description to add; baseline 4 applies. The description correctly implies the target is implicitly "the open change" rather than something selected by argument.

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?

"Undo every edit of the open change by restoring the files as they were, and close it" gives a specific verb (undo) and resource (the open change), plus the exact mechanism (restore files) and side effect (close the change). It is distinguishable from ecu_change_finish by implication, but it never names that sibling, so an agent must infer the discard-vs-commit split.

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?

Usage is implied by the phrase "the open change" – an agent can infer this applies only while a change is open and that it is the abort path – but there is no explicit statement of when to use it over ecu_change_finish or ecu_change_diff, and no mention of a prerequisite that a change must exist.

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