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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), but the description adds substantial context beyond them: the exact response keys, that invalid relational schemas are refused here with the reason, and that 'version' is a concurrency token for the following save. That is real behavioral disclosure an agent needs for the next 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?

Front-loaded with the core verb and constraint, then cleanly bulleted. The ANSWER paragraph is long but justified given there is no output schema, though the opening clause mildly restates the tool title.

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?

With no output schema, the description carries the return contract (applied, diff, summary, plan, version) and the failure mode, all of which an agent needs to act on the result. Nothing material is missing for a 3-param preview tool.

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%, so the baseline is 3, but the description adds meaning the schema does not: which project types each of schema/operations applies to and that operations is exactly the payload patch_schema or drop_schema_items would take. project_id semantics are left to the schema, which is fine for a UUID.

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 (preview a schema change) and immediately contrasts it with the siblings it mirrors: patch_schema and drop_schema_items, which actually save. The phrase 'saving nothing ... before it is saved' makes the preview-only nature unmistakable against the mutate siblings.

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?

Explicitly routes the caller: pass ONE of operations (relational projects) or schema (relational or graph), and states it is 'the one way to see what a change would do before it is saved'. It also tells the agent to feed the returned version into the subsequent save as expected_version, giving forward guidance no sibling provides.

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