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

Annotations declare readOnlyHint, idempotentHint, and non-destructive behavior. The description goes beyond by revealing that the tool returns specific fields (station id, name, country, coordinates, pollutants with sensor ids, resolved_place), explains radius defaults (12 km) and max (25 km), and clarifies that location is required for filtering. It does not contradict any annotations.

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 four sentences, each serving a distinct purpose: listing search methods, describing return fields, stating usage context, and emphasizing location requirement. It is front-loaded with the core action, uses no filler, and every sentence earns its place. Excellent structure.

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's relative simplicity (read-only query with 8 parameters, no output schema), the description fully covers the necessary information: search methods, return values, parameter details, and usage constraints (requirement for location argument). No gaps are apparent; an agent would have sufficient context to invoke this tool 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?

Input schema has 100% description coverage, providing baseline 3. The description adds value by explaining that '_apiKey' is optional (gateway supplies one), that 'city' can include country for ambiguous names, and that 'radius_km' has defaults and max. It also clarifies that 'bbox' expects a specific string format. These details enhance understanding beyond the schema alone.

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 'Find OpenAQ air-quality monitoring stations by location' and enumerates four distinct search methods (city, coordinates+radius, country, bounding box). It also explicitly differentiates this tool from sibling 'get_measurements' by framing it as the first step for historical series, which helps the agent select the correct tool.

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 strong context on when to use this tool: 'first step for a historical series: find the station here, then pass its sensor_id to get_measurements.' It also explicitly states 'At least one location argument is required — the tool will not return an unfiltered global list,' which prevents misuse. However, it does not explicitly mention when not to use it or provide alternatives to sibling tools like 'air_quality_near', though the differentiation is implicit.

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