usgs_earthquakes

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

Annotations already convey that the tool is read-only, idempotent, open-world, and non-destructive. The description adds context about return fields (magnitude, location, depth, time, alert level, tsunami risk, felt reports) and magnitude scale interpretation, which is useful. However, it does not disclose potential rate limits, pagination behavior, or response volume, which could matter for heavy queries. Since annotations cover safety, the description is adequate but not rich.

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 three sentences, each carrying useful information: the search scope, the return fields, and the magnitude scale context. It is not bloated and gets to the point quickly. The magnitude scale is front-loaded near the end, which is a sensible structural choice. No unnecessary words.

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 moderate complexity (10 optional parameters, all documented) and a rich annotations set (readOnly, idempotent, openWorld), the description covers the essential aspects: what it does, what it returns, and how to interpret magnitude thresholds. It lacks details on potential API limitations, such as default date ranges or result count limits, but the schema covers the 'limit' parameter. Overall, the description is sufficiently complete for an agent to call it correctly for typical queries.

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 100%, meaning all 10 parameters are already described in the schema. The description adds the magnitude scale guidance (2.5+ felt, etc.), which helps infer the meaning of minmagnitude/maxmagnitude. However, for other parameters like latitude/longitude/maxradiuskm, the description adds nothing beyond the schema. The schema is comprehensive, so this is a standard baseline.

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 states a specific verb ('Search for earthquakes') and resource ('earthquakes'), along with key query dimensions (magnitude, location, date range). It clearly distinguishes the search function from sibling tools like usgs_earthquake_count and usgs_significant, which serve different purposes (counting, listing significant earthquakes).

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 clearly states the purpose and provides meaningful magnitude scale context, which helps agents decide if this tool is appropriate for a query (e.g., if the user asks for earthquakes felt by people, the agent knows to set minmagnitude=2.5). However, it does not explicitly mention when to choose an alternative tool, such as usgs_earthquake_count for counts, or mention any exclusions.

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