Skip to main content
Glama
Sign In

Smarter Weather

by io.github.smarterweather
OverviewDiscussionsAdmin

Get context

get_context
Read-onlyIdempotent

Where a place is and what time it is there. query (a name, ZIP, venue or address) or lat+lon to ranked candidates with lat/lon, timezone and type place|zip|address|poi|county|station; time: utc and, per distinct zone among the candidates, its local time and a 14-day calendar (join on timezone). Sun and moon are get_data reads. Example: {"lat": 39.74, "lon": -104.99} -> Denver, America/Denver.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_context"
  }
}

Input Schema

NameRequiredDescriptionDefault
latNoLatitude (-90 to 90), with lon; not with query.
lonNoLongitude (-180 to 180), with lat.
fuzzyNoQuery only: autosuggest for partial or misspelled input. Default false.
limitNoQuery only: how many candidates (1-10). Default 5.
queryNoPlace name, ZIP or venue/address (1-200 characters); not with lat/lon.
includeNoboundaries: each row's state, county and zone ids for get_data's area.
near_latNoQuery only: rank near this point (-90 to 90); with near_lon.
near_lonNoLongitude of near_lat (-180 to 180).

Output Schema

NameRequiredDescriptionDefault
latNo
lonNo
timeYes
queryNo
partialNoSections that did not finish, e.g. {"poi": "timeout"}; the list may be incomplete.
candidatesYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent, open-world, non-destructive. The description adds behavior beyond that: candidates are ranked, time is per distinct zone among the candidates, and the 14-day calendar joins on `timezone`. It is silent on ranking criteria and default limits, but the added context is meaningful.

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?

Front-loads the purpose, then inputs, then outputs, then a worked example — a sensible order. It is extremely compressed and telegraphic (semicolon-clause fragments), which is efficient but risks being parsed as cryptic on first read. No sentence is clearly wasted.

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

Completeness4/5

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

An output schema exists, yet the description still sketches the return shape (candidates, time, per-zone calendar) and how to join time to candidates, which is the key integration detail. Given eight optional parameters and no required ones, it covers what an agent needs; only edge behavior (errors on ambiguous query, limit interaction with time rows) is absent.

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. The description still adds value by explaining the mutual exclusivity of the input modes and, importantly, that `include: boundaries` supplies state/county/zone ids that feed get_data's area queries — a usage meaning the schema alone does not convey.

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

Purpose4/5

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

Opens with a concrete statement of what it returns: geographic position plus local time for a place. The two input modes (query vs. lat/lon) and the candidate types are spelled out. It does not name a closest sibling (e.g., find_places or get_time_context) to contrast with, so the differentiation bar for a 5 is not met.

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

Usage Guidelines4/5

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

Gives explicit alternative paths (a name/ZIP/venue/address via `query`, or a point via `lat`+`lon`) and an exclusion: sun and moon belong to get_data reads, which routes the agent away. It does not state when to prefer this over find_places or get_time_context, so it stops short of full when/when-not guidance.

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
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources