Portugal (public data)

wildfires

Burnt areas from wildfires in Portugal, mapped by satellite (EFFIS / Copernicus).

Not a live list of fires in progress: EFFIS maps burnt areas from satellite a day or more later, and small fires can be missing. Args: period: "today", "week", "month" or "season" (this year so far). Ignored when year is given. year: a past year from 2016, for the whole year. place: keep fires whose region or parish contains this, e.g. "Algarve", "Monchique", "Viseu". min_hectares: only fires at least this large. sort: "area" (largest first) or "date" (newest first). limit: max fires listed (totals always cover every match).

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": "wildfires"
  }
}

Input Schema

Name	Required	Default
`sort`	No	area
`year`	No
`limit`	No
`place`	No
`period`	No	season
`min_hectares`	No

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 11, 2026

TDQS

A4.6/5.0

Behavior4/5

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

With no annotations present the description carries the full burden, and it delivers the two traits that matter most for this data: a mapping lag of a day or more and known under-coverage of small fires. It also discloses that totals always cover every match even when `limit` truncates the list. What it does not cover is permissions, rate limits, or data licensing.

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

Conciseness5/5

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

Two framing sentences front-load the most decision-relevant fact (this is retrospective burnt-area data, not a live feed), followed by a tight per-argument list. Every line adds information; nothing is padding.

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?

For a six-parameter, fully-optional query tool with an output schema and no annotations, this is complete: all parameters are explained, the data's latency and coverage limits are disclosed, and return formatting is correctly left to the output schema.

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

Parameters5/5

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

Schema description coverage is 0%, yet the description documents all six parameters with meaning the schema cannot convey: the four valid period values and their interaction with year, the 2016 lower bound on year, substring matching against region or parish for place, and the two concrete sort modes. The limit/totals distinction in particular resolves an ambiguity the bare integer type leaves open.

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 names the concrete resource (burnt areas from wildfires), the geographic scope (Portugal) and the source (EFFIS / Copernicus satellite mapping). It immediately distinguishes itself from live-fire siblings by stating it is 'not a live list of fires in progress', so an agent can separate it from active_incidents or fire_risk without opening any schema.

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?

The 'not a live list' framing tells the agent when NOT to use this tool and implies the live-incident alternative, and the arg notes clarify the period-vs-year precedence. What is missing is an explicit named alternative for in-progress fires and any guidance on choosing between period and year beyond the ignore rule.

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

All Portugal (public data) tools Inspect

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.