USGS Earthquakes

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

With no annotations provided, the description carries the full burden. It discloses the return fields (magnitude, location, depth, felt reports, tsunami status, tectonic summary) and notes 'when available,' adding conditional behavior. However, it does not mention error handling for invalid IDs or net behavior, but for a simple read tool this is adequate.

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 brief but complete: a clear purpose sentence, a list of return fields, and a concise parameter explanation. It is front-loaded and every sentence adds value, with no unnecessary filler.

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 single-parameter tool with an output schema present, the description covers the necessary context: what the tool does, what it returns (including optional fields), and how to use the parameter. The presence of an output schema means return structure is already defined, so the description is sufficiently complete.

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 provides only a title 'Event Id' with 0% coverage, so the description is essential. It defines the parameter as a USGS event ID, gives a concrete example ('us7000m1xh'), and explains how to obtain IDs ('from search results'). This fully compensates for the schema's lack of description.

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 explicitly states 'Get full details of a specific earthquake event by its USGS event ID.' This clearly identifies the action (get details), the resource (specific earthquake event), and the identifier (USGS event ID). It is well-distinguished from siblings like get_recent_earthquakes (lists events) and get_earthquakes_near (geo-filtered list).

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: this tool is for a specific event known by an ID, and it instructs 'Get IDs from search results.' This implies usage after a search/list call, but it does not explicitly name alternatives or state when not to use it. Sibling tool names are visible in context, but the description itself does not draw explicit comparisons.

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

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

No annotations are provided, so the description carries the full burden. It discloses defaults and maximum values for radius_km and days, which is helpful. However, it omits behavioral details such as how results are ordered, any result limits, or the nature of the returned data (though output schema may cover return structure). It is not misleading but lacks depth, scoring a 3.

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: two clear sentences of purpose, then a concise Args block. Every sentence earns its place, though the Args section could be more compact. It is not bloated and remains readable, so a 4 rather than a 5 for slight verbosity.

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?

With 5 parameters, no annotations, and an output schema present, the description covers the parameters and use cases thoroughly. It does not describe return values, but the output schema handles that. It could mention result ordering or edge cases like 'no earthquakes found,' but overall it is complete enough for correct invocation, earning a 4.

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 description includes an Args section that explains every parameter: latitude/longitude with examples, radius_km with default and max, min_magnitude with default, and days with default and max. This adds substantial meaning beyond the input schema, which has no descriptions at all. The schema coverage signal is 0%, meaning the description fully compensates, so a 5 is appropriate.

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 the tool 'Get earthquakes near a specific geographic location' and 'Searches for earthquakes within a radius of the given coordinates.' This distinguishes it from siblings like get_earthquake_detail (specific event lookup) and get_recent_earthquakes (recent list, not location-scoped). The verb+resource+scope are specific and unambiguous.

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 explicit use cases: 'Useful for assessing local seismic risk or investigating felt reports.' This tells when to use the tool. However, it does not explicitly mention when not to use it or point to alternatives among siblings, so it misses exclusions. Clear context but no exclusions warrants a 4.

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

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

No annotations are provided, so the description carries the full burden. It discloses that results come from the USGS catalog and are sorted by time (newest first), which is useful behavioral context. However, it does not cover potential behaviors like delay in catalog updates, error handling, or whether results are limited by USGS API specifics. This 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 front-loaded with the primary purpose, followed by a clear statement of the data source and ordering, then a brief use case, and finally structured parameter details. Every sentence contributes value, and the length is appropriate for the tool's complexity.

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?

The tool is simple with 3 optional parameters and an output schema exists, so return values don't need explanation. The description covers purpose, behavior, parameter semantics, and a use case. It does not discuss relationship to sibling tools or potential edge cases, but for a straightforward read-only API, this is nearly complete. Missing explicit sibling differentiation slightly reduces completeness.

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 has 0% description coverage, but the Args section fully explains all three parameters: min_magnitude (with default and guidance for 'significant quakes'), days (with default and max), and limit (with default and max). This adds meaning beyond the schema's types and defaults, fully compensating for the lack of inline schema descriptions.

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+resource combination: 'Get recent earthquakes worldwide above a minimum magnitude.' It clearly distinguishes this from siblings by emphasizing 'worldwide' and 'recent', and names the USGS catalog as the data source. This is a precise and unambiguous purpose.

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?

It states a clear use case: 'Useful for monitoring seismic activity globally.' This provides context, but it does not explicitly mention when to use sibling tools like get_earthquake_detail or get_earthquakes_near, nor does it exclude alternatives. The absence of exclusions keeps it at 4 rather than 5.

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