Air trend

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

Beyond the annotations (readOnlyHint, idempotentHint), the description discloses important behavioral nuances: time_above_threshold_minutes integrates real sample spacing and is affected by sensor downtime, and it warns to check coverage_ratio and last_sample_at before treating results as full-window figures. This goes well beyond the basic safety profile and genuinely helps an agent understand data quality caveats.

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 dense yet well-organized: it opens with the core purpose, then details the statistical outputs and the important caveat about coverage_ratio, and closes with usage examples. Every sentence contributes meaningful information without redundancy. Despite its length, it remains highly scannable and front-loads the key purpose.

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 there is no output schema, the description compensates by explicitly listing the returned fields (mean, median, min, max, current, rate_of_change_per_hour, etc.) and the optional natural-language observation. It also mentions fallback behavior for locationId and the effect of pollutant='all', covering the essential contexts an agent needs to correctly call and interpret results. No critical gaps remain.

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 already provides descriptions for all 5 parameters (100% coverage), so the baseline is 3. The description adds value by explaining the effect of pollutant: 'all' (array + worst_pollutant) and mentioning privacy_mode's impact, but it doesn't elaborate on hours, locationId fallback, or response_format beyond what the schema states. No parameter is left undocumented, but the description provides only modest additional semantic depth.

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 it performs 'Windowed trend analysis for PM2.5 / CO2 / VOC' and lists the exact return metrics (mean, median, etc.). It distinguishes itself from siblings by focusing on past measurements and trends, while tools like air_current_reading imply current state. The inclusion of example questions ('is PM2.5 climbing?') further clarifies its intent.

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 an explicit 'Use this for ...' statement with concrete example queries, which effectively communicates when to invoke it. However, it does not explicitly mention when not to use it or name alternative sibling tools for other scenarios, leaving some room for interpretation. The context is clear but lacks explicit exclusions.

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