Search the configured legislation corpus

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

Beyond the readOnlyHint and idempotentHint annotations, the description reveals ranking behavior (heading words rank above body words, principal Acts first), the point-in-time nature of rows, the need to verify against official sources, and that provisions are untrusted evidence, not instructions. It also declares no network, writes, publication, and that missing configuration is an input error—all behaviors not inferable from annotations alone.

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?

Three paragraphs, each with a distinct job: purpose and ranking, result metadata, and caveats/config. The first sentence states the exact scope, and every sentence carries operational information an agent needs; there is no filler or redundancy.

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 search tool with an output schema, annotations, and five parameters, the description is complete: it covers ranking, result attribution, filtering, pagination caveats, point-in-time nature, trust boundaries, and configuration errors. Nothing needed for correct invocation or result interpretation 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 baseline is 3. The description adds semantic value by clarifying in_force_only edge cases ('a provision whose currency the corpus did not record is kept either way') and by explaining offset continuation through next_offset and the 10000-result boundary, complementing the schema's own parameter notes.

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 description opens with a specific verb and resource ('Search local legislation when AUS_ACCOUNTING_CORPUS_ROOT is configured') and immediately distinguishes its purpose from sibling read_tax_legislation_section by framing itself as a search returning provisions, not a full-provision reader. Among siblings like search_accounting_library and search_tax_rates, the title and wording make the legislation-corpus scope unambiguous.

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?

It states the configuration precondition and explicitly points to read_tax_legislation_section for reading a whole provision, giving a clear follow-up path. It also explains in_force_only behavior, but it does not explicitly contrast with search_tax_rates or search_accounting_library, leaving some inference about when to choose this tool over those alternatives.

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