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

Annotations cover the safety profile (readOnlyHint, openWorldHint), so the bar is lower. The description adds real behavioral context beyond them: it defines the comparison baseline, discloses the fallback when no yesterday snapshot exists, and notes that observed-actual verification is only present 'where actuals exist' — useful expectation-setting with no output schema to lean on.

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?

A single dense sentence with the primary purpose front-loaded and no filler. The nested em-dashes and parenthetical do make it harder to parse, but every clause carries information rather than padding.

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 3-optional-param read tool with no output schema, the description supplies the essential return semantics: it is a diff, the comparison window is yesterday-or-earlier-today, and verification appears only where actuals exist. Only minor gaps remain, such as not restating the city-roster vs lat/lon choice (already in schema).

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 100%, so the three optional parameters (lat, lon, city) are already documented, including the lat/lon ranges and the city roster hint. The description only reinforces the 'US location' restriction, adding little beyond the schema — baseline 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?

States a specific verb+resource: how a US location's forecast *changed* since yesterday, plus forecast-vs-observed verification. The 'diff other weather sources cannot show' framing implicitly separates it from the plain `forecast` sibling, but no sibling is named explicitly and the second clause ('plus forecast-vs-observed verification') folds in a distinct capability, slightly blurring the one-line purpose.

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 'or since earlier today when yesterday has no snapshot yet' clause explains a data fallback rather than when to pick this tool over `forecast`, `history_today`, or `why_this_forecast`. Usage is implied (ask this when you want a delta) but there are no explicit when/when-not rules or named alternatives.

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