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

Annotations already declare write/non-destructive/non-open-world, so the safety bar is lower. The description adds real context beyond them: that omitting it yields generic-labelled versions whose history becomes unreadable and therefore unrestorable, and that the label is surfaced verbatim to the user. It does not mention permissions or persistence semantics.

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?

Front-loads the core action, then the workflow pattern, then the rationale for using it. Every sentence carries weight, though the all-caps emphasis and repetition of the label-intent point add slight noise.

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 two-parameter write tool with no output schema and annotations covering the safety profile, this covers purpose, workflow, and the cost of skipping it adequately. What a saved version returns and how it relates to restore_version/diff_versions is not addressed.

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 100% and both parameters are described there, including the user-facing intent guidance for label and the access-refusal behavior for expectedProjectId. The description's label advice largely restates the schema, so baseline 3 is appropriate.

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 ('Saves a NAMED version of the current state') and uses the 'NAMED' qualifier to distinguish itself from the automatic generic-labelled versions it contrasts with. An agent immediately understands this is the explicit-snapshot tool, not an implicit one.

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?

Gives a concrete use pattern ('save_version("before the overhaul") → writes → save_version("Q3 overhaul")') plus the consequence of omission, which effectively states when to use it. It never names its siblings (restore_version, list_versions, diff_versions), so routing among version tools is left to inference.

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