版を戻す

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

With no annotations, the description carries the full load, and it does disclose the crucial destructive trait: any change made after reverting discards all versions beyond the revert point, while the file itself survives. This is exactly the kind of irreversible side effect an agent must know before calling. It stops short of covering permissions, rate limits, or whether the revert itself is undoable.

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?

One sentence with the core action front-loaded and the caveats in a parenthetical immediately after. Every clause carries information: the operation, the non-deletion guarantee, and the forward-history loss. Nothing is wasted.

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 2-parameter mutation tool with no annotations and no output schema, the description covers purpose and the main destructive consequence. It could go further by saying whether the score_id remains valid after a revert or what the call returns, but the essential contract is present.

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 50%: score_id is documented in the schema (from score_open), while steps only has type/default/bounds. The description compensates by explaining that steps means how many versions to move back, which adds semantics beyond minimum/maximum 1–100. The default of 1 is left to the schema and not restated, which is acceptable.

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 states a specific verb (戻す/revert) applied to a specific resource (今の版/current version) and names the controlling parameter (steps). No sibling overlaps with this operation (score_save, score_open, score_render, etc. are all non-reverting), so an agent can identify it immediately, though the description never explicitly contrasts itself with a sibling.

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?

Usage is implied by the verb 'revert' plus the constraint that the file itself is not deleted, which signals this is a history operation rather than a delete. However, there is no explicit statement of when to prefer this over, say, re-opening or comparing versions, and no prerequisites (permissions, whether score_save is needed first) are given.

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