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

Beyond the sparse readOnlyHint/idempotentHint annotations, the description reveals important behavior: refs are validated against existing goal-owned rows, the Planner computes the repeat verdict server-side, and only admitted certificates influence the numeric rework rate. It stops short of covering prerequisites, auth, or failure/return behavior, which keeps it below a 5.

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?

Three dense sentences with the core verb and object up front; the rest packs validation requirements, a conditional rework rule, and a business-consequence statement with no filler.

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 12-parameter tool with no output schema, the description covers the high-risk acceptance rules and the business impact, while the schema covers field-level semantics. It does not explain how a 'current tracked contract' is established or what the call returns, which are minor gaps given the sibling context and the record action.

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 parameters are already documented; per the baseline this is a 3 unless the description adds substantial new meaning. It reinforces and links artifactRefs, addressesFindingIds, and repeatCheckEvidenceId, but most of that relationship is already present in the schema descriptions rather than being newly disclosed here.

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 names the exact action ('Record'), object ('one completed LeanSolver iteration'), and context ('current tracked contract'), so an agent can distinguish it from generic goal-update or finding-registration siblings. The final sentence also states its exclusive effect on the rework rate, further sharpening purpose.

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 clearly says the tool applies to completed iterations and gives concrete invocation conditions: artifact refs must be owned evidence and rework iterations require registered finding IDs plus repeatCheckEvidenceId. It does not explicitly name sibling tools or give a when-not-to-use alternative, so it falls just short of full routing guidance.

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