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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, covering the safety profile. The description adds useful behavioral context beyond those: it searches across the entire network, returns prices, locations, photo counts, and seller verification status, and supports typed filters and radius. No contradiction with annotations.

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?

The description is three sentences, each earning its place: the first states scope and item types, the second provides usage guidance, the third summarizes return fields. No filler, no redundancy, and the key information is front-loaded.

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 11 parameters, nested objects, and no output schema, the description is quite complete: it explains what is searched, when to use it, and what the results contain. It does not mention pagination or sort options, but those are documented in the schema. Annotations cover non-determinism. It could go slightly deeper, but overall makes the tool safely invocable.

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 55%, so the description carries some responsibility. It references 'typed filters, a price range and a radius around a place', which maps to filters, minPrice/maxPrice, and radiusKm, and it lists example item kinds for the 'kind' parameter. However, it does not explain all parameters (e.g., page, sort, limit) and repeats some info already in the schema. Decent but not exceptional.

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 uses a specific verb ('Search') and clearly identifies the resource ('individual items across every business on the network'), enumerating concrete item types (property listings, vehicles, courses, etc.). It also explicitly distinguishes itself from the sibling tool 'search_businesses' by noting the preference for items over companies.

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?

The description gives an explicit usage directive: 'Prefer this over search_businesses whenever the user is looking for a THING rather than a company.' This provides clear when-to-use guidance and names an alternative. It does not explicitly state when not to use it, but the preferential language effectively covers the main exclusion.

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