undo_last_vault_change

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

With no annotations supplied, the description carries the full burden and does so: it discloses that the undo is itself recorded as a new commit (so calling again redoes the change), that a stale `commit` causes nothing to be undone plus an error, and what the mutation does node-by-node.

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?

Roughly ninety words, front-loaded with the core action before alternatives and edge cases. Every sentence adds information: semantics, trigger, fallback, parameter rule, and return shape.

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 single-parameter mutation tool with no output schema, it covers semantics, error behavior, and the return payload name list. The one uncovered case is what happens when the vault has no commit to undo, which an agent would want to know.

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 coverage is 0%, so the description must compensate, and it does: `commit` is identified as the hash returned by the bad write, with a minimum length of 7 characters, an omitted-value default (newest commit), and a precise stale-hash failure mode.

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 names a specific verb and resource (undo the newest vault commit) and then spells out the per-node semantics: a created node is removed, a changed or deleted node is restored. It explicitly distinguishes itself from history_vault and restore_vault, so an agent can route correctly without opening any 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?

It gives an explicit trigger ('Use it right after a write that went wrong') and an explicit exclusion with the alternative to use instead when later writes have landed. It also pins down when the `commit` argument should be supplied, which is the main selection nuance for this tool.

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