compare_locations

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

With no annotations, the description carries the behavioral burden and does substantial work: it enumerates all six comparison criteria with their semantic meanings (e.g., 'driest: Lowest precipitation probability'), describes the ranked output shape, and implies aggregation across multiple locations. It does not disclose potential multi-API-call cost or failure behavior for invalid locations, but the criteria and return-structure detail go well beyond the schema.

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-organized with clear bolded headers, a front-loaded summary of purpose, and no wasted sentences in the criteria or args sections. The Examples block is mildly redundant with the criteria and usage sections, making it slightly longer than strictly necessary, but each section still earns its place.

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 0% schema coverage, no annotations, and a loose input schema, the description must bear the full explanatory load — and it succeeds. It covers every parameter's semantics, defaults, and valid ranges, enumerates all criteria values, explains the output structure (criteria, ranked locations, winner, details), and gives usage scenarios. Nothing needed to invoke the tool correctly is missing.

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 0%, and the description fully compensates. For 'locations' it specifies the required dict keys ('name', 'latitude', 'longitude') that the loose 'additionalProperties: true' schema omits. For 'criteria' it documents every valid value with a definition despite no enum in the schema, and for 'forecast_days' it adds the 1-16 valid range beyond the bare integer type.

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 states a specific verb and resource — 'Compare weather conditions across multiple locations' and 'Rank locations by specified weather criteria to find the best destination.' This clearly distinguishes it from single-location siblings like get_weather and get_air_quality, and the multi-location scope is explicitly stated.

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?

A dedicated 'Use this tool when' section lists concrete trigger scenarios: choosing between multiple destinations, planning group activities, and finding optimal conditions for specific activities. It provides clear context but does not name alternatives or state when not to use it (e.g., no explicit 'for a single location use get_weather'), so it falls short of the full when/when-not standard.

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