Sample climate baseline for an area by pulling a few addresses

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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, so the safety profile is covered. The description adds meaningful behavioral context: it returns both aggregate and per-URL responses for transparency, it avoids N redundant fetches when samples agree, and it notes that limitations of the per-property tool apply (e.g., no landslide coverage). This goes beyond the annotations without contradicting them.

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 a single dense paragraph that front-loads the core behavior and then explains the use case and limitations. It is efficient and every sentence earns its place, though it could be slightly more scannable with a break between the behavior and usage guidance.

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 read-only sampling tool with one parameter and no output schema, the description covers the key context: what it returns, when to use it, and a known limitation. It doesn't describe the exact response shape, but the absence of an output schema and the tool's simple aggregate-return nature make this a minor gap. The mention of the per-property tool's limitations is a good completeness touch.

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 single parameter sample_urls is well-described in the schema. The description adds value by explaining the purpose of the parameter (representative URLs for the area) and the expected count (2–10), which reinforces the schema's min/max constraints. It doesn't add syntax details, but with one fully documented parameter, the baseline is high.

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 clearly states the tool fetches climate risk for a small set of representative URLs, averages their baseline values, and returns a shared cluster_id when present. It distinguishes itself from per-property climate tools by emphasizing the area-level sampling approach and explicitly naming the alternative (per-property call).

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 explicitly says to use this as a cheap area-level read BEFORE fanning out per-property calls, and explains the condition under which it applies (all sample properties agree on cluster_id and factors). It also gives a concrete usage pattern: pass 2–10 representative URLs. This is strong when-to-use guidance with a clear alternative.

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