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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is known. The description adds genuinely new context that softens and clarifies that profile: unsaved work is captured as its own checkpoint first, so the restore is not lossy. It does not cover authorization needs or whether the restore is itself reversible.

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 short sentences, zero waste, with the action stated first and the side-effect reassurance immediately after. Nothing could be removed without losing meaning.

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 mutation with no output schema, the description covers what the action does and its main side effect. The remaining hole is provenance of the commit hash, which an agent must infer from the list_checkpoints sibling.

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 only 50%: projectId is documented (pointing to list_projects) but commit has no description at all beyond a hex pattern. The description says nothing about either parameter, so it does not compensate for the gap or explain that the commit hash comes from list_checkpoints.

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 gives a specific verb and resource ('Returns the site to an earlier checkpoint'), which is clearly distinct from save_checkpoint and list_checkpoints. It does not explicitly name those siblings, so differentiation comes from the verb rather than from routing language.

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 only implied: an agent can infer this is the rollback action opposed to save_checkpoint, but the description never states when to prefer it or any prerequisite such as first listing checkpoints. No exclusions or alternatives are named.

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