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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive, so the safety profile is covered. Beyond that the description adds genuinely useful behavior: the query is interpreted deterministically with no model call, and the response reports how the sentence was parsed including unused words. Minor residual tension with openWorldHint is not a contradiction, since 'offline, calls no model' refers to the parsing step, not data access.

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 short sentences, front-loaded with the callable example, then the return shape, then the determinism guarantee. No filler and nothing buried.

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?

An output schema exists, so return values need not be enumerated, and the description still sketches the key return concept (listings plus parse explanation). Combined with annotations covering safety, the definition is nearly complete; only edge behavior such as unmatched or unparseable queries and the input length limit 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?

With one parameter at 0% schema coverage, the description must carry the semantics, and it does: it tells the agent the input is a full sentence with a worked example ('short .com under $500 that accepts offers') and notes that unused words are reported back, which guides query construction. The 300-character cap and any parsing limits are still undocumented.

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 gives a concrete verb+resource (search listings from a natural-language sentence) and an inline example that pins down the shape of the input, so the agent knows exactly what this tool does. It does not explicitly distinguish itself from the sibling search_domain_listings (structured search), so the boundary between the two is left to inference.

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?

Usage is implied by the 'plain English' framing and the example sentence, which suggests this is the entry point when the user has an unstructured query rather than facet filters. However, there is no explicit when-to-use/when-not guidance and no sibling tool is named as an alternative, so the agent must infer that search_domain_listings is the structured counterpart.

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