redo_last_edit

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

Annotations already indicate destructiveHint=true and idempotentHint=false, so the description does not need to restate those. The description adds the qualifier 'in-memory,' which implies the edit is not persisted to disk and is part of a session-level undo/redo stack. It does not disclose failure conditions (e.g., no undone edit exists) or whether the expected_revision parameter affects rollback behavior, but the annotations cover the core safety profile. The added 'in-memory' context is a minor enhancement.

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?

The description is a single, precise sentence with no waste. It is front-loaded with the verb 'redo' and clearly introduces the action. However, it omits needed detail such as parameter explanations, which technically are part of completeness but the brevity itself is commendable. It is appropriately sized for a simple operation, though the lack of parameter info might be a missed opportunity.

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?

The tool has two parameters (one required), an output schema, and a destructive nature. The description only states the action; it does not explain the meaning of expected_revision, error cases, or the in-memory nature is not expanded. With no usage guidelines beyond inference and no parameter semantics, an agent may not know how to properly invoke it, especially since there is a param that likely controls optimistic concurrency. The output schema exists but its relationship to the function (e.g., what is returned after a successful redo) is not mentioned. The description is insufficient for a reliable call.

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 schema description coverage is 0%, so the description must compensate. It does not mention either project_id or expected_revision. The description only references 'the last undone edit' without explaining how project_id selects the target project or what expected_revision is used for (e.g., a concurrency guard). The agent receives no parameter semantics from the description, leaving all meanings to the property names, which is insufficient for a tool with one required param and a complex output schema.

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 clearly identifies the action (redo) and the target (last undone in-memory edit). It is distinct from the sibling tool undo_last_edit and specifically describes the unique operation. The verb 'redo' is unambiguous, and 'last undone' provides a clear scope typical of a redo action.

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?

The description clearly states what the tool does but does not explicitly say when to use it. It implies usage after an undo operation via the phrase 'undone in-memory edit,' and the sibling name undo_last_edit suggests a pairing. However, it lacks explicit guidance on preconditions (e.g., must have previously undone an edit) or when not to use it, so the usage context is only implied.

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