List rule changes

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint false, closed world), and the description builds on that with ordering, the fields each change carries, pagination via has_more/cursor, and the version id to hand to resolve_version. It goes further with an auth prerequisite ("Needs an API key whose plan includes the change feed; otherwise the error says so") and a scope disclaimer, which are exactly the behaviors annotations cannot express.

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?

Front-loaded with purpose and ordering, then mechanics, then the auth caveat, which is a sensible progression with no repeated clauses. It is dense and runs long for a list tool, and the trailing "Informational only, not legal advice" is boilerplate that does not help an agent invoke it, though it is only one clause.

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?

There is no output schema, yet the description still tells the agent what comes back (rule identity, from/to versions, effective date, version id) and how to detect and handle more pages. Together with the auth and jurisdict ion caveats, nothing needed to call this six-parameter tool correctly is missing.

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 schema already defines every parameter and the baseline is 3. The description earns above that by supplying a full example payload and, critically, explaining the consequence of the jurisdictions array — that each slug matches only its own rules, so multi-level coverage requires listing both levels. That practical implication is not derivable from the schema's terse "each matches its own rules only".

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 and resource ("List changes to published rules") and enumerates exactly what a change is: new versions, amendments, corrections, repeals. It also specifies ordering ("oldest first"), which separates it from a point-in-time sibling like get_rule_as_of, so an agent can distinguish it from the surrounding tools without opening a 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 concrete operational guidance: a worked example call, the cursor loop ("While `has_more` is true, call again with the response's `cursor`"), and the non-obvious jurisdiction rule about also passing the federal level for complete Washington coverage. It does not explicitly route away from alternatives such as get_rule_history for a single rule, so the when-not-to-use case is left implicit.

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