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

Beyond the destructive and non-idempotent annotations, it discloses that this get persists reviews and refreshes comparison values and the approval version, while leaving finding decisions to humans. It does not explain exactly what the refresh overwrites or what makes the operation destructive, so the concrete impact remains somewhat opaque.

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?

It front-loads the result, then covers side effects and the safety boundary in two compact sentences with no filler. The slash-heavy terminology and subjectless “persist reviews, refresh...” wording are dense enough to require careful parsing.

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 reconciliation operation with unexpected writes, it covers the required run state, returned differences, persistence behavior, and approval guardrail. With no output schema, additional detail about the returned finding/review structure, precise refresh consequences, and run-ID discovery would make it more complete.

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?

Both parameters already have schema descriptions and UUID formats, so the baseline is 3. “Completed” adds an implicit run-state constraint, but the description does not clarify that the generic `id` is the contract ID or provide guidance for obtaining either ID.

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?

It identifies the resource and result—differences between a completed re-read and saved fields—and separately states the review-persistence and comparison-refresh behavior. The prohibition on applying, settling, or dismissing findings also distinguishes it from clm_apply_contract_reconciliation.

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?

“Completed” scopes use to a finished re-read, while “Never apply/settle/dismiss findings” establishes an explicit when-not boundary. Requiring person approval in Contracko supplies a concrete alternative for those decisions, making the review-versus-decision boundary clear.

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