get_typical_weather

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

With no annotations, the description carries the full burden of behavioral disclosure. It clearly states this is historical data, not a forecast, and explains that the year in the dates only fixes the calendar window while the summary covers complete past years. It also describes the return contents (average high/low, extremes, rain count). It lacks explicit statements about side effects or error conditions, but for a read-only historical query the description provides adequate behavioral context.

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 well-structured and front-loaded: the first line states the core purpose and non-forecast nature, followed by usage context, return details, and a behavioral note. While it spans multiple paragraphs, each sentence contributes essential information without fluff. It could be tightened slightly but remains efficient and easy to scan.

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?

Given the tool has no output schema and four parameters, the description covers the essential return data (averages, extremes, rain count) and explains the critical usage context (forecast horizon and replacement by get_forecast). It addresses the year parameter's semantics and the historical nature. Minor gaps like error handling or explicit response format are not covered, but the description is sufficiently complete for an agent to invoke the tool correctly and interpret results.

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?

The schema provides 100% description coverage for all parameters, setting a baseline of 3. The description adds semantic value beyond the schema, particularly for the year aspect: it clarifies that the year in the dates is used only to fix the calendar window and that the summary always covers complete past years. This nuanced interpretation is not in the schema and helps agents avoid misusing the year field. The description also implicitly explains the 'years' parameter by mentioning 'over recent years'.

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 returns observed historical weather data for a date window, explicitly contrasting with forecasts. It names the resource (typical weather) and the action (get), and distinguishes itself from sibling tools like get_forecast by highlighting the historical vs forecast nature. The purpose is unambiguous and specific.

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 gives explicit guidance on when to use this tool: for trips beyond the 16-day forecast horizon, and explicitly states when not to use it — once dates fall within 16 days, get_forecast replaces it. It names the alternative tool directly and instructs not to keep quoting averages. This is a model example of usage guidance.

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