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

Goes well beyond the annotations: explains that it 'runs the real checks, then undoes every change', that it 'saves nothing', what it returns ('the resulting state and effects'), and the permission requirement. This clarifies the meaning of readOnlyHint=true for a tool that transiently executes checks, and adds a security note about untrusted CRM field content.

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?

Well front-loaded: the dry-run purpose leads, followed by usage, permissions and return behavior in tight sentences. There is mild redundancy in restating 'without saving it', 'undoes every change', and 'saves nothing' three ways, and the trailing untrusted-content warning is generic boilerplate rather than tool-specific.

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 very complex tool (22 params, deep nested objects, 6 required fields, no output schema) the description covers purpose, usage, permissions and side effects, which is solid. However it does not help the agent navigate which parameters belong to which action, a significant gap at 5% schema coverage for a schema this large.

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 5% across 22 parameters (only workspaceId is documented), so the description carries the burden and largely does not. It only implicitly maps the prose operations to the 'action' enum (transition/close/reopen/correct); the other ~20 parameters, including large nested objects like finalTerms/correctedTerms, receive no explanation of when they apply per action.

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 (tests/previews) plus the exact operations it covers (stage move, close, reopen, closure correction) and makes clear it is a dry-run of those mutations. This lets an agent distinguish it from transition_record_stage, close_record, reopen_record and correct_closure without opening any schema.

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 clear usage context: 'Use it to show the user what a change would do', notes it 'Needs the same access as the change itself', and warns that 'the real call checks everything again' — implying the preview does not replace the actual mutation. It stops short of explicitly naming the sibling mutation tools as the alternatives, so it is strong but not exhaustive.

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