fix

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

With no annotations, the description carries the full burden, and it delivers: it explains that the same deterministic checks run, that models only choose a repair, that replacing published records waits for human approval, that creating absent records does not stop, and that report_file is always written. This is rich behavioral disclosure beyond what the schema provides.

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?

The description is long but structured and front-loaded with the core purpose. Every paragraph adds a distinct behavioral or operational point: repair scope, approval gates, reporting artifacts, and degraded-agent mode. Some phrases are cryptic ('munim approve answers without it'), which prevents a 5.

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 tool with no annotations and no output schema, this covers the important operational dimensions: what is repaired, what is off-limits, how approvals work, reporting artifacts, and behavior with agents off. A clearer statement of the returned status or resolution result would make it fully 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?

Schema coverage is 100%, and the description does not add much parameter-level detail beyond the schema. It indirectly relates to 'target' via the client/domain resolution, but it does not explain dkim_selector or otherwise deepen the parameter picture. Baseline 3 is appropriate.

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 first sentence names an explicit action ('repair what can be repaired safely') and a clear resource ('a client's domain'). It also distinguishes itself from the sibling 'check' tool by saying 'check explains what is wrong. This acts on it.'

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?

The description gives usable context: use this when you want to act on check results, and use 'check' for diagnosis. It also references 'apply_mail_setup' for approvals. It stops short of an explicit when-to-use vs. when-not-to-use list, but the alternatives are named and meaningful.

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