dns_change

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

With no annotations, the description carries the full burden and does well: it discloses the dry-run default, that the plan shows each record before and after, that records are read back after apply, the one-A-record-per-name invariant, and that planHash is single-use and invalidated by target state changes. It omits auth/permission requirements and any rate or concurrency behavior.

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?

A single dense sentence front-loads the tool's identity and per-mode semantics, then closes with the plan/apply/read-back lifecycle. Every clause carries information, though the run-on density would benefit from light structural separation.

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 high-risk mutation tool with nested objects, no annotations and no output schema, the description covers the workflow, safety gate (planHash), and return behavior adequately. Missing permission/precondition detail keeps it short of 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 description coverage is only 40%, and the description compensates by explaining the three array/object parameters (set = name→IP create-or-update, move = every A record on one IP to another, remove = by name or by IP) plus the apply/planHash relationship already documented in the schema. The proxied flag and the set-item structure are left to the schema, so it is not fully exhaustive.

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 concrete verb (change A records in Cloudflare) and enumerates the three distinct sub-operations - set, move, remove - with their exact semantics. An agent can distinguish each mode from the sibling read-only tool dns_records 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?

Clear operational context: dry run is the default and apply requires a planHash from the very same call, with guidance that the plan is refused if targets changed. It does not, however, name an alternative sibling (e.g. dns_records for inspection) or state when this tool should be preferred over one.

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