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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world). The description adds value beyond them by scoping results to 'published information' and stating the citation-oriented return shape (ids, titles, source URLs), though with an output schema present the return detail is somewhat redundant.

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 tight sentences, front-loaded with purpose before workflow and example. The example is illustrative rather than filler, and no sentence is wasted.

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 single-parameter, richly-annotated tool with an output schema, the description covers purpose, scope, return shape, and the downstream fetch workflow. Nothing an agent needs to call it 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% and the param docs are minimal ('What to look up'), so the baseline would be 3. The concrete natural-language example query ('second mortgage LVR for a trust') adds real meaning about the expected query style that the schema does not convey.

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 (searches) and resource scope (Switchboard Finance's published information on Australian business finance types, criteria and licensing). Crucially it distinguishes itself from the sibling 'fetch' by explaining that it returns ids/titles/URLs while fetch delivers full text.

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?

Clearly routes the agent: search first, then 'pass an id to fetch for the full text'. It gives context for the search-then-fetch workflow but does not state when to prefer other siblings such as check_fit or list_products, which could be relevant alternatives for the same domain.

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