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

Annotations already declare destructiveHint=true and idempotentHint=false, but the description adds material behavior well beyond them: the exact scope of destruction (schema + code, not Neo4j data), the post-rollback API redeployment, single-operation-per-project locking with a named blocking job, and the transient RationalBloks refusal. These are the details an agent needs before firing an irreversible call.

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?

Purpose is front-loaded, the warning follows immediately, then recovery instructions. Almost every sentence carries operational weight; the final RationalBloks sentence is somewhat verbose but still actionable, and nothing is redundant with the annotations.

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 destructive, irreversible-looking mutation with no output schema, the description covers scope, side effects, and error/retry handling thoroughly. Remaining gaps are minor: no mention of what the call returns or how the environment parameter interacts with the rollback.

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 100%, and the description's only param-adjacent information ('commit SHA of the version you want to rollback to', discoverable via get_graph_version_history) restates the schema. It says nothing about the environment parameter's effect on a rollback, so it does not exceed the baseline.

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 ('Rollback a graph project to a previous version') and immediately scopes it with what is and is not reverted (schema AND code yes, Neo4j data no). It does not explicitly distinguish itself from the sibling rollback_project, so an agent must infer the graph vs. non-graph split from the name alone.

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?

It tells the agent exactly how to prepare ('Use get_graph_version_history to find the commit SHA') and how to recover from the two documented refusal conditions (wait via get_job_status and retry; retry in a few minutes during RationalBloks updates). There is no explicit 'do not use this when...' alternative, but the operational routing guidance is unusually strong.

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