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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavioral context beyond that: it uses Gemini for translation, executes one to three parallel structured searches, merges and ranks results, and returns up to 9 listings with match scores, interpretation, and unresolved items. This gives the agent a solid mental model of how the tool behaves internally.

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 front-loaded with the most important information (what it does and when to use it). It then flows into the internal mechanism and the return value. It is slightly longer than necessary, but every clause adds distinct information (parallel searches, merging, ranking, count, match scores, explanation) without redundancy.

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 2-parameter tool with no nested objects and an output schema, the description is rich enough. It covers scope ('Spanish properties','PropertyList's full MLS'), process, and what the agent will receive back. Annotations cover safety and idempotency, and the output schema likely explains the return shape. The only slight gap is not describing edge cases like language mismatches or external API dependencies, but that is minor.

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 description coverage is 50%, with the 'brief' parameter already well-described (plain-English/Spanish, 10-500 chars). The description enriches that by clarifying what makes a good brief (vague, conditional, lifestyle-heavy) and provides an example. However, it adds no semantics for the 'language' parameter, which is left entirely to the enum values. Since the schema carries some of the load and the description supplements the brief, a 3 is appropriate.

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 starts with a clear, specific verb and resource: "Match Spanish properties from a free-form description." It immediately distinguishes itself from the sibling search_properties (likely structured queries) by focusing on free-form, vague, lifestyle-heavy briefs. The mechanism, using Gemini to convert the brief into parallel structured searches, further clarifies the tool's unique function.

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 statement 'Best for vague, conditional, or lifestyle-heavy briefs' provides explicit guidance on when to choose this tool. It also gives a concrete example of an appropriate brief. However, it does not explicitly state when not to use it or name the structured alternative (e.g., search_properties), so while the context is clear, the exclusion is only implied.

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