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

Annotations already declare readOnly/idempotent/openWorld/destructive=false, yet the description adds substantial behavioral context: data provenance, inclusion of dates/uncertainty/attribution/licenses, source/freshness metadata, and the critical caveat that source-check time differs from observation time. These are non-obvious traits that meaningfully change interpretation.

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 first sentences front-load purpose and sources well, but the text repeats the same caveats twice ('no sightings does not establish absence' / 'No records does not mean the animals are absent'; man-of-war-as-siphonophores stated twice). The trailing 'Units: ft, kt, s, F, mi; directions FROM' line is irrelevant boilerplate for an observation-listing tool lacking unit-bearing parameters.

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 no output schema, the description does describe returns ('data and source/freshness metadata') and provides rich interpretation caveats. Combined with the nested query schema, an agent has enough to call it correctly, though the bbox format gap 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?

Schema description coverage is 0%, so the description must carry the load. It explains limit's default (20) and maximum (100) and says bbox narrows the sample, but it never explains the bbox string format (e.g., minLon,minLat,maxLon,maxLat), which is the riskiest undocumented parameter for a nested query object.

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?

States a specific verb+resource (published Florida jellyfish, box jellyfish and man-of-war observations) and names the sources (OBIS and iNaturalist). It clearly differentiates itself from siblings like get_observations, get_shark_research, and get_red_tide by scoping to jellyfish/man-of-war and clarifying these are published records rather than live warnings.

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?

Gives explicit context and exclusions: it is 'not live tracking, beach warnings, abundance estimates or swimming-safety scores,' and 'Never apply NOAA's Chesapeake sea-nettle forecast to Florida.' It also tells the agent to use bbox to narrow the sample. It stops short of naming a specific alternative sibling tool, but the when-not guidance is strong.

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