nearby_hazards

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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive, so the safety profile is covered. The description adds real behavioral context beyond that: graceful degradation when FIRMS_MAP_KEY is unset or FIRMS fails, with a firms_note explaining why, plus the fact that limit caps both result sets and hotspots are returned nearest-first. It does not describe result ordering for events or response shape, keeping it at 4.

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?

Front-loaded with the core purpose and tight overall, with every clause carrying operational meaning except 'day_range is 1 to 5', which merely restates the schema's minimum and maximum. Minor redundancy, but the ordering is sensible and there is no filler prose.

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?

There is no output schema and no annotations-led return description beyond the mention of firms_note. For a tool that merges two heterogeneous sources (EONET events vs FIRMS hotspots) with six parameters, the description should say something about what each source's records look like or how to tell them apart in the response. Adequate for calling, incomplete for interpreting results.

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%, so the description must carry parameter meaning. It clarifies limit's dual capping behavior and day_range's 1-5 window, and latitude/longitude/radius_km are self-evident from naming. The source parameter with its eight-item VIIRS/MODIS/LANDSAT enum is left entirely unexplained — the single most consequential omission for a caller choosing a satellite dataset.

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 statement: 'Open EONET events and FIRMS hotspots within radius_km of a latitude and longitude.' That makes the combined-source nature clear enough that an agent can distinguish it from single-source siblings like fires_near and eonet_events. It stops short of explicitly naming the siblings as alternatives, so a 5 is not warranted.

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 a genuine exclusion ('Not for safety-of-life decisions') and explains the FIRMS fallback, which is useful usage context. However, it never states when to prefer this tool over sibling tools such as fires_near or eonet_events, nor any prerequisites such as FIRMS_MAP_KEY being needed up front. Usage is implied rather than directed.

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