USGS Earthquakes

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

Describes comprehensive return data fields and availability caveats ('when available'), though omits traits like idempotency or error conditions.

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?

Compact, front-loaded purpose statement followed by return value details and Args section; no wasted 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?

Adequate for a single-parameter lookup tool; mentions key return fields even though output schema exists, reinforcing agent understanding.

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?

Excellent compensation for 0% schema coverage by providing concrete example ('us7000m1xh') and provenance hint ('Get IDs from search results').

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?

Clear specific verb (Get full details) and resource (earthquake event by USGS ID), distinguishing it from sibling list/search tools.

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?

Implies workflow ('Get IDs from search results') but lacks explicit when/when-not guidance comparing to get_recent_earthquakes or get_earthquakes_near.

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 provided; description compensates by disclosing constraints beyond schema (max 20001km radius, max 365 days) and defaults, though omits rate limits or auth requirements.

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?

Well-structured with front-loaded purpose followed by mechanics, use cases, and Args section; every sentence adds value beyond structured data, though 'Args:' format is slightly verbose.

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 output schema exists and parameters are simple scalars, the description adequately covers inputs; could briefly mention coordinate system (WGS84 implied) but omissions are minor.

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?

Excellent compensation for 0% schema description coverage: provides concrete examples (37.7749 for San Francisco), units (kilometers), and constraint boundaries not present in structured schema fields.

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?

Specific verb-resource pair ('Get earthquakes near a specific geographic location') clearly distinguishes this location-based search from siblings 'get_recent_earthquakes' (time-based) and 'get_earthquake_detail' (specific event retrieval).

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?

Provides explicit use cases ('assessing local seismic risk or investigating felt reports') but lacks explicit 'when not to use' guidance or comparison to siblings.

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?

Discloses USGS data source, sorting order (newest first), and constraint limits (max 30 days, 500 results) not present in annotations or schema.

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?

Well-structured with purpose front-loaded, followed by behavior, use case, and Args section; no redundant or filler text.

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?

Thorough coverage given output schema exists; minor gap in explicit sibling differentiation, though 'worldwide' provides implicit contrast to 'near'.

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?

Comprehensive compensation for 0% schema description coverage by explaining all 3 parameters, their defaults, and usage guidance (e.g., 4.5+ threshold).

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?

Explicitly states it retrieves recent earthquakes worldwide above a minimum magnitude, distinguishing from sibling 'near' (location-based) and 'detail' (single event) tools.

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?

Provides use case ('monitoring seismic activity globally') and magnitude guidance (4.5+ for significant quakes), though could explicitly contrast with location-specific sibling.

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