undo_multiple

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

Annotations already cover the destructive/read-write profile, yet the description adds real behavior beyond them: it stops early at real stack depth or an undo barrier rather than erroring, and it flags the critical 'actually_undone < requested' oracle for detecting stack exhaustion. That is exactly the kind of non-obvious trait (clamping instead of failing) an agent cannot get from the annotations or schema.

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-loaded with the action, then usage, then the warning, then return fields. It is short and every sentence carries distinct information (what, when, caveat, return contract) with no filler.

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?

There is no output schema, so the inline 'Returns:' block spelling out requested/actually_undone/undo_count is necessary and provided. Combined with full parameter documentation and annotation coverage of the mutation profile, nothing an agent needs to call this correctly is missing.

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?

With 100% schema coverage on the single 'count' parameter, the schema already documents the >=1 constraint and the silent capping. The description restates that capping behavior rather than adding new syntax or format detail, 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?

States a specific verb and resource ('Walk the undo stack back N transactions') and immediately scopes it as a multi-step variant. An agent can distinguish it from the singular 'undo' sibling and from 'redo_multiple' without opening the schema.

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 use case ('unwind a whole failed batch') and describes the early-stop condition, which is clear guidance on context. It does not explicitly name the single-step 'undo' alternative or state when not to use it, leaving the single-vs-batch routing implied.

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