Portugal (public data)

open_data_search

Search the datasets of Portugal's national open-data portal (dados.gov.pt).

Args: query: e.g. "acidentes rodoviários", "escolas", "qualidade do ar", "alojamento local". organization: optional publisher to filter by, e.g. "INE", "Lisboa" or "Câmara Municipal de Cascais" (a town name finds its town hall's datasets: Lisboa, Porto, Cascais, Oeiras...). limit: max results (1-50).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "open_data_search"
  }
}

Input Schema

Name	Required	Description	Default
`limit`	No
`query`	Yes
`organization`	No

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 11, 2026

TDQS

B3.3/5.0

Behavior2/5

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

No annotations are supplied, so the description carries the full behavioral burden. It never states matching behavior (title vs. full text), pagination/total counts, accent or language handling, or rate limits, and only incidentally reveals mutation-free intent through the word 'search'.

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 purpose is front-loaded in a single sentence, followed by a compact Args block with one line per parameter. No filler, though the parenthetical list of town names is slightly repetitive with the example before it.

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

Completeness3/5

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

With three parameters, no annotations, and an output schema present, the definition is mostly sufficient, but it omits how results relate to the follow-up dataset tool and what the search actually matches against, leaving an agent to discover ranking and paging behavior empirically.

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 description coverage is 0%, so the description must compensate and largely does: it gives concrete query examples in Portuguese, explains that organization accepts a publisher or a town name (with the non-obvious behavior that a town name resolves to its town hall), and states the 1-50 range for limit.

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?

States a specific verb and resource: 'Search the datasets of Portugal's national open-data portal (dados.gov.pt)'. That is unambiguous about what is searched and where, though it never distinguishes this catalog-listing tool from siblings like open_data_dataset or open_data_preview.

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

Usage Guidelines3/5

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

Usage is only implied by the examples given for query and organization; there is no explicit statement of when to use this search versus fetching a dataset directly or using the other statistical sources (INE, BPStat). An agent must infer the search-then-retrieve workflow.

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.