redo_multiple

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

Annotations already declare destructiveHint=true and idempotentHint=false, but the description adds crucial non-obvious behavior: the silent cap, the early stop without error, and the warning to compare actually_redone against requested. This is exactly the kind of edge-case signal an agent needs.

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?

Front-loads the action and its stopping behavior, follows with a targeted warning, then documents the return shape. Three tightly written sentences plus a compact return summary; every sentence earns its place.

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 no output schema, the description supplies the return fields and how to interpret them, plus the redo-stack wipe behavior. An agent has everything needed to call the tool and correctly interpret partial results.

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%, so the count parameter is already fully documented. The description's 'N undone transactions' aligns with the schema but adds no new syntax or constraints; the WARNING concerns output interpretation, not the input parameter.

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: 'Re-apply N undone transactions in one call.' The 'N' and early-stop behavior distinguish it from the single-step redo sibling, and it is clearly not an undo tool.

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?

Explains it stops early rather than erroring and that new edits wipe the redo stack, which tells the agent when a no-op result is legitimate. It does not explicitly name sibling alternatives like redo or undo_multiple, so routing guidance is implied rather than complete.

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