Search Leginova (full text)

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

Annotations already cover the safety profile (readOnly/idempotent/non-destructive), so the description uses its space for genuinely additive behavior: default AND semantics, exact-phrase quoting, operator keywords, the shape of each result (official URL to cite plus a `next` tool call), and the scope→facets→filters round-trip. This is real behavioral context beyond structured fields.

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?

Dense but front-loaded: what it searches, then query grammar, then result shape, then facet loop, then the alternative-tool caveat. Every sentence carries information, though the single block is long and could be broken up for faster scanning.

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?

Given 11 parameters, nested `filters`, an output schema, and a rich set of 13 siblings, the description supplies what the schema cannot: the query language, the facets/filters workflow, and routing to leginova_get_code_article. Since an output schema exists, it correctly avoids describing return values in detail.

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 parameters are already well documented and the baseline is 3. The description adds meaning the schema lacks: that `scope` must be restricted for facets, that facet values flow back through `filters`, and that queries are French-language with a specific operator grammar. It does not cover date or pagination semantics, which the schema handles.

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+resource ('full-text search across the official law of New Caledonia on leginova.gouv.nc') and enumerates the covered collections (JONC, consolidated texts, codes, case law, Congress debates). It explicitly distinguishes itself from the sibling leginova_get_code_article for article-by-number lookups.

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 when-to-use guidance (write queries in French, use scope to get facets, feed facets back through filters) and an explicit when-not: an empty result is not proof a rule doesn't exist, and to fetch a code article by number use leginova_get_code_article. Query-operator semantics (AND default, quotes for exact phrase, OU/SAUF) are documented in the description itself.

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