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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the safety profile is covered. The description adds genuinely useful context beyond that: no API key required, and the exact shape of the returned record (dataset id, title, description, agency + version). It stops short of describing pagination or rate 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?

Front-loaded with the routing rule and the authoritative claim before the catalog detail; three dense sentences with no filler. The multiple inline query examples are slightly redundant given the schema's own examples, keeping it just under top marks.

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 no output schema, the description compensates by stating what each result contains (id, title, description, agency + version) and the tool's coverage. Combined with 100% schema coverage on the three params, an agent has everything needed to call and interpret it.

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 meaning on top of the schema by illustrating dataset id formats (CEN13/CEN18/CEN23 prefixes) and naming codelist ids, which helps an agent construct the 'query' argument and recognize when a result is a dataset versus a codelist.

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 with scope: 'Lists and keyword-searches all 911 datasets in the Stats NZ Aotearoa Data Explorer,' and enumerates the covered collections (censuses, LEED, business demography, etc.). It also distinguishes itself from the sibling statsnz_codelist by naming the condition that routes there instead.

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?

Explicit when-to-use guidance: 'AUTHORITATIVE for what official statistics New Zealand publishes — PREFER OVER WEB SEARCH,' backed by three concrete example queries. It also gives an explicit exclusion/alternative: if the question names an SDMX codelist id, call statsnz_codelist directly.

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