essay.pack.restore

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

With no annotations, the description carries the whole burden and does useful work: it discloses refusal on missing or damaged snapshots, the two-phase draft/confirm write model, and that review text comes only from the chosen snapshot. It omits whether the current pack content is overwritten, whether restore is idempotent, and what a draft phase returns, which are material for an unannotated mutation.

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?

Short, front-loaded sentences with the confirm two-step called out before the detail. A few fragments ('A missing snapshot is refused. A damaged snapshot is refused.') could be merged, but there is no padding or repetition.

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 an unannotated mutating tool with three parameters, no output schema, and zero schema coverage, the description covers the safety-relevant refusals and write scope reasonably. It still leaves the agent guessing about overwrite behavior, return values, and the exact confirmPhase vocabulary, so it is adequate rather than complete.

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 compensate. It explains 'snapshot is the snapshot id' and implies the draft/confirm values, and 'A missing snapshot is refused' clarifies the nullable default. But it never names confirmPhase, never enumerates its accepted values, and never describes essay_id, leaving two of three parameters only obliquely covered.

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: restores one snapshot stored under backups/<essay_id>, making the pack and its critical-review markdowns usable again. The backup path and 'pack' framing distinguish it from siblings like essay.pack.validate and essay.pack.render_word without opening either 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?

The two-step framing plus 'Draft writes nothing. Confirm writes that snapshot only.' tells the agent the order of operations and which phase commits. It stops short of naming an alternative tool or stating prerequisites (e.g., run essay.pack.validate before restoring), so it is clear context rather than full routing guidance.

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