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

With no annotations provided, the description carries the full burden—and it delivers. It discloses the statistical methods (Theil-Sen and Mann-Kendall), robustness properties, return format ('summary' with plain-English and statistical details), and clamping behavior for out-of-range years including metadata.years_clamped. It even gives interaction instructions ('Present the summary to users first').

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: a clear purpose sentence, methodology, return value, then an Args section. Each sentence provides necessary information without fluff. The front-loading of the core action and the explicit arg format makes it easy to parse.

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 tool with no output schema, the description adequately explains the return value ('summary' with plain-English description and statistical details) and key behaviors like clamping. Given the moderate complexity and 3 parameters, no critical information is missing. It is complete for an AI agent to select and invoke correctly.

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%, but the description fully compensates. It explains all three parameters: location accepts postcode, place name, or 'lat,lon'; pollutant lists valid options and default; years specifies default, range, and clamping behavior. This exceeds typical schema documentation.

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 opens with a specific verb and resource: 'Analyse the long-term trend in a pollutant near a location.' It clearly distinguishes from sibling tools like get_current_aq (current conditions) and get_historical_aq (raw historical data) by focusing on long-term trend analysis with explicit statistical methodology.

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 provides clear context for when to use this tool: for long-term trend analysis to determine improvement, worsening, or stability. It also notes robustness to outliers and missing data, implying suitability for noisy datasets. However, it does not explicitly state when not to use it or reference alternative tools, so it lacks the explicit exclusions seen in top-tier examples.

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