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

Annotations already carry the safety profile (destructiveHint=true, idempotentHint=true, readOnlyHint=false), so the bar is lower. The description adds useful context that the restored version is 'retained' and that the result becomes 'the next version,' implying additive versioning rather than in-place overwrite, plus the manual narrative obligation. It does not contradict the annotations, though it leaves the concrete destructive effects unspecified.

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?

Two sentences with no filler and the core action front-loaded. The second sentence earns its place by flagging a mandatory manual step. Slightly more structure (e.g., separating the narrative requirement from the main action) could improve scanability, but it is appropriately compact.

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?

This is a destructive, 6-parameter, nested-object tool with no output schema and no parameter descriptions; the two-sentence description is insufficient. It omits what happens to the current graph/version, failure semantics (e.g., expectedProjectVersion mismatch), whether the operation is reversible, and what the response indicates.

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 0% schema description coverage, the description must compensate, but it only clarifies changeNarrative (that it must contain four plain-language sections, matching the schema's four required fields). Nothing is said about expectedProjectVersion's optimistic-concurrency role, restoreVersion's range semantics, idempotencyKey's purpose, or projectId/sessionId.

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 uses a specific verb-resource pair ('Republish a retained prior graph version as the next version') that clearly conveys restoring an older version by publishing it as a new one. It distinguishes itself from siblings like publish_project_graph and clear_project_graph by the 'retained prior version' qualifier, though it does not name those siblings explicitly.

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?

No guidance is given on when to use this tool versus alternatives such as publish_project_graph, export_project_graph, or list_project_versions. The only usage note is the manual changeNarrative requirement, which is a workflow constraint rather than selection guidance; no exclusions or conditions are provided.

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