Replenishable-water availability at a point. Free tier = public GRACE groundwater trend; authenticated tier adds a derived (non-locating) replenishable-atlas indication.
| Name | Required | Description | Default |
|---|---|---|---|
| lat | Yes | ||
| lon | Yes | ||
| depth_m | No | ||
| authenticated | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover readOnly, idempotent, openWorld, and non-destructive behavior. The description adds meaningful context beyond those: the data source (GRACE groundwater trend), the two-tier behavior, and the 'non-locating' property of the authenticated atlas indication. This gives the agent useful behavioral expectations without contradicting annotations.
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?
Two sentences with no filler. The core purpose is front-loaded, and the second sentence concisely conveys the free-vs-authenticated distinction. Every clause adds value.
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, yet the description does not describe the return value's shape, resolution, or units. It also does not explain depth_m or how the point is interpreted. The tier behavior is helpful, but for a tool with four parameters and no output schema, this is not complete enough for confident invocation.
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 compensate. It explains the authenticated parameter's meaning indirectly and implies lat/lon define the point, but depth_m is completely unexplained, and units or coordinate conventions are not given. This is only partial compensation for the schema gap.
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 names a specific resource (replenishable-water availability) and a clear scope (at a point). It implicitly distinguishes itself from sibling tools like ground_stability or seismic_hazard by focusing on water, but lacks an explicit verb or named sibling comparison, so it falls just short of a 5.
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 gives useful tier-selection guidance: free tier uses public GRACE data, authenticated tier adds a derived atlas indication. However, it does not explicitly say when to choose this tool over alternatives like resource_indication or ground_stability, so usage guidance remains implied rather than explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
ground_truth aggregates the same water/stability/hazard/resource answers offered by individual tools, and check_hypothesis/verify/list_nulls all inhabit the trust/provenance space, so an agent may hesitate between options. The descriptions are detailed enough to resolve most selections, but the overlap is real and not just one or two edge cases.
All names use snake_case, but the style is mixed: some are bare nouns or noun phrases (capabilities, ground_stability, water_availability) while others are imperative verbs (check_hypothesis, list_nulls, run_controlled_test, verify). This is readable but lacks a single consistent verb_noun convention.
Eleven tools is a well-scoped size for an Earth-grounding service; each tool earns its place by covering a distinct capability like querying hazards, checking hypotheses, running controlled tests, or verifying anchors. The set is neither bloated nor thin.
The set covers the advertised five-question answer surface plus verification, hypothesis checking, nulls, and space-weather risk, giving agents a solid query-test-verify lifecycle. Minor gaps exist around contributing new nulls or hypotheses, but the core workflows have no dead ends.