Skip to main content
Glama

Smarter Weather

by io.github.smarterweather

Get forecast skill map

get_forecast_skill_map
Read-onlyIdempotent

Measured forecast skill as a map of res-4 hexes inside a bounding box, sliced from the public skill map. Use this when the question is spatial ("where is NBM temperature skill weak across Colorado"), not "how good is the forecast at this point" — that is get_forecast_skill. Requires model, variable, lead_hours, and bbox {west,south,east,north}. lead_hours selects the containing published bucket (20 → NBM 24); a lead we have not published returns no slices rather than a nearby one. A hex is included when its center is inside the box; edge-overlapping hexes are dropped. The box cannot wrap the dateline. Each cell is [h3, samples, skill_score]; skill_score is unitless (fraction of climatological variance explained) and already gated at n ≥ 30. withheld lists hexes still accumulating. Do not compare slices across models or truths. This is CELL# only — never treat a hex as a person.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
bboxYesBounding box {west,south,east,north}. Hexes whose H3 center falls inside are returned.
modelYesModel id, e.g. nbm, gfs, hrrr, or rrfs.
domainNoOptional domain (conus, alaska, hawaii). Omit unless you already know it.
variableYesVerified variable, e.g. temperature_2m, dew_point_2m, precipitation, or precipitation_gt_0p254mm.
lead_hoursYesLead time in hours; the containing published bucket is selected. Never approximated.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
bboxYes
slicesYes
generated_atYes
atom_resolutionYes
minimum_samplesYes

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Added

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the readOnly/idempotent annotations, the description discloses lead-time bucket selection, hex-center inclusion rules, dateline restrictions, cell shape [h3, samples, skill_score], the n ≥ 30 gating, withheld hexes, and the warning not to compare slices across models or truths. This is substantial behavioral context that annotations alone do not provide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense but front-loaded with the core purpose and spatial-vs-point routing. Nearly every sentence carries behavioral or usage value; only the line "Requires model, variable, lead_hours, and bbox" is somewhat redundant with the required fields in the schema, and "CELL#" is slightly cryptic.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the nested bbox parameter, output schema, and nuanced slicing behavior, the description covers all the important call-time concerns: spatial interpretation, lead bucketing, inclusion rules, dateline restriction, return cell format, and gating. Nothing critical is missing for an agent to invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds meaningful semantics: lead_hours "selects the containing published bucket (20 → NBM 24)", no-slice behavior for unpublished leads, and bbox interpretation via hex center. These details go beyond the schema's property descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and object: "Measured forecast skill as a map of res-4 hexes inside a bounding box," which clearly distinguishes it from the point-based sibling. It also explicitly contrasts itself with get_forecast_skill, so an agent can disambiguate without inspecting schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states exactly when to use this tool: "Use this when the question is spatial ... not 'how good is the forecast at this point' — that is get_forecast_skill." It also gives exclusionary edge cases, such as "returns no slices rather than a nearby one" and "The box cannot wrap the dateline," which tell an agent when the tool will not behave as expected.

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

All Smarter Weather toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.1/5.0
Disambiguation4/5

Most tools have clearly distinct purposes, and the detailed descriptions generally prevent misselection. A few near-overlapping pairs exist — get_current_conditions vs get_observations, and get_forecast already bundling current conditions, alerts, and outlooks — so some ambiguity remains.

Naming Consistency4/5

The overwhelming majority of tools follow a get_<object>_<modifier> pattern in snake_case, and the non-get tools still use an imperative verb_noun form. The mix of verbs (get, list, describe, find, query, search, reverse) is a minor inconsistency, but the overall pattern is predictable.

Tool Count2/5

At 32 tools, the surface is heavy and exceeds the 25+ threshold for a large tool set. The weather domain justifies much of the breadth, but several tools overlap in scope and could plausibly be consolidated, making the count feel higher than necessary.

Completeness5/5

The tool set comprehensively covers current conditions, forecasts, hourly data, climate, alerts, severe weather, air quality, tropical systems, upper-air soundings, maps, model data, geocoding, and platform status. There are no obvious dead-end workflows, and raw access via query_dataset fills most remaining gaps.

Resources