Search the configured ATO rulings

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

Beyond the annotations (readOnly, idempotent, non-open-world), the description discloses a lot the structured fields do not: no network, writes or publication; missing configuration is an input error; rows are point-in-time copies that may be withdrawn or amended; and retrieved text is untrusted evidence that never acts as instructions. The prompt-injection warning and currency caveat are exactly the kind of behavioral context an agent needs.

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 purpose and precondition are front-loaded in the first sentence, and most sentences carry real payload (ranking, row_ref linkage, currency caveat, injection warning). It is dense and slightly overstuffed — the sentence about edited private advice is narrow — but nothing is padding at the level of a wasted sentence.

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?

With an output schema present, the description need not enumerate return fields, yet it usefully names docid, family, title, paragraph label, source_url, fetch date, page hash and row_ref for read_ato_ruling. Combined with the config-error and reliability caveats, an agent has what it needs to call and interpret the tool; only explicit alternative-tool routing 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 description coverage is 100%, so all four parameters (query, limit, family, offset) are already documented, and the description does not add format or syntax detail for them. It does explain ranking behavior ('words as a phrase in a title or heading rank above the words in body text'), which clarifies how query results are ordered, but that is output behavior rather than parameter semantics, so the baseline 3 applies.

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 gives a specific verb and resource ('Search local ATO rulings') plus a configuration precondition, which cleanly separates it from sibling corpus tools like search_tax_legislation and search_accounting_library. It does not explicitly name an alternative, but the resource scope is unambiguous enough that an agent can select it correctly.

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 states a precondition (AUS_ACCOUNTING_RULINGS_ROOT must be configured) and a post-retrieval obligation (read the Legal Database page before relying on a result), which implies when to use it. However, it never contrasts itself with the sibling search tools or says when this corpus is the wrong choice, so routing guidance is only implied.

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