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

Annotations already establish readOnly, idempotent, non-destructive, non-open-world, so the safety profile is covered. The description adds genuinely useful behavior: token cost per size (~321 line, ~566 week, ~1,567 table, ~1,564 series, ~647 rain line), the credits requirement, and the page URL to cite. It does not explain error behavior or how many forecast sources are actually consulted.

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?

It is front-loaded with what the tool returns and wastes few words, but the notation is telegraphic ('line ≈321 tok', 'size=runs:') and the second half is a dense run-on of mode variants that requires re-reading. Information density is high, but structure and readability suffer.

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 15-parameter tool with no output schema, the description does a solid job of sketching output shape and cost per size, and it flags the two major mode branches (runs and rain). Gaps remain around what 'median/spread' means across mixed sources and around several secondary parameters, but the core is covered.

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 93% schema coverage the baseline is 3, and the description earns more by explaining mode-specific semantics the schema does not: that size=runs surfaces each source's newest run with run_utc/fetched_at and that NBM additionally emits XND, P12 and Q12, and that variable=rain reports members' share of >=0.01in with n = model families. Still, several params (stn, win, credits enum values, include_6h) get no narrative elaboration.

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 opening sentence gives a concrete verb+resource: daily high/low for a place aggregated across every free forecast, plus rain, obs, alerts, credits and page URL. It is unmistakably a forecast-reading tool, but it never names a sibling to distinguish it from 'fetch' or 'history', so differentiation 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?

Mode selection guidance is present in fragments ('size=runs: one place, each source's newest runs by day', 'variable=rain: ...'), which tells the agent when to pick those modes. There is no statement of when to prefer this tool over fetch/history/sources, and no exclusions or prerequisites. The 'Keep the credits and link the page' line is attribution guidance, not tool-selection guidance.

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