curator_restore

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

Annotations already declare destructiveHint=true and idempotentHint=true; the description adds real context on top by explaining that a lesson restore replaces an existing same-slug section or re-adds it, and that a skill restore replaces the primary dir and mirrors it to configured roots. What's missing is any mention of what the optional pass_id controls and how the target snapshot is selected.

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?

Four short sentences, front-loaded with the core action, then the invocation constraint, then the two mode-specific behaviors. No filler and no repetition of schema fields.

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?

An output schema exists, so return values need no explanation, and the mutation semantics are well covered. The gap is pass_id: with 0% schema coverage and no required parameters, an agent has no way to know whether omitting it restores from the latest snapshot or fails, which is material for a destructive tool.

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 0%, so the description must carry parameter meaning, and it only partially does: it explains the mutual exclusivity of lesson_slug and skill_name but says nothing at all about pass_id, which is left as an unexplained empty-defaulted string. Two of three parameters get real semantics, one gets none.

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+resource ('Restore one lesson or skill from a curator pre-mutation snapshot') and scopes it to a single item. It does not, however, distinguish itself from the sibling lesson_restore, which an agent could easily confuse it with.

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 a concrete invocation rule ('Pass exactly one of lesson_slug or skill_name'), which is genuine usage guidance beyond the schema. But it never says when to use this versus lesson_restore or curator_run, nor when the snapshot-based path is the right choice over a plain lesson restore.

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