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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), so the description adds what annotations cannot: the output is a probabilistic forecast with a range, is bounded to a 30-day park-local window, and is not a live measurement. It does not mention rate limits or failure modes, but for a read-only forecast that is a minor gap.

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 usage condition and prerequisite, with each sentence carrying distinct information (when to use, prerequisite, output nature). No filler.

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?

With no output schema and full parameter coverage, the description correctly spends its budget on when-to-use and what the response conceptually is (forecast and range). Enough for correct invocation, though it could say more about the forecast's shape or granularity.

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%, so date, days, and park_id semantics are already fully documented. The description only reinforces the park-ID prerequisite and the 30-day horizon, adding no syntax or format detail beyond the schema; baseline 3 applies.

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?

Specific verb+resource ('how crowded one supported park may be'), explicit scope (next 30 park-local days), and an explicit contrast with what it is not ('not a guarantee or a live wait'), which cleanly separates it from parky_get_waits. An agent can distinguish this from siblings without opening any schema.

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?

States the triggering user intent and a prerequisite ('Resolve the park ID first'), and implicitly routes live-wait questions elsewhere via 'not ... a live wait'. It never names the alternative tool explicitly, so routing for edge cases is left to inference.

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