Skip to main content
Glama

Search Curitiba open datasets

open_datasets_search
Read-onlyIdempotent

Search the Curitiba open data catalogue by query to find dataset IDs, titles, publishers, and detail-page URLs for follow-up file access.

Instructions

Search the Portal de Dados Abertos de Curitiba catalogue. Returns dataset ids, titles, publishers and detail-page URLs; pass an id to dataset_files. Read-only (the portal search is a form POST).

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_datasets_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
queryYesSearch term in Portuguese. The portal matches accents literally: try 'saúde' and 'saude'.

Output Schema

NameRequiredDescriptionDefault
dataYes
fetched_atYes
source_urlYes
license_noteYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered. The description adds genuinely non-redundant context by explaining that the read-only search is implemented as a form POST, pre-empting an agent's confusion about a POST-based read, and it sketches the return fields for chaining. It stops short of noting rate limits or result pagination beyond the limit cap.

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?

Three short sentences, each doing distinct work: identity, return shape plus handoff, and read-only caveat. No filler and the most important routing information is front-loaded.

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, so the return-field sentence is bonus rather than necessity, and the read-only/POST caveat covers the main behavioral surprise. The only gap is the unexplained limit parameter for a search tool where result volume matters.

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

Parameters3/5

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

Schema coverage is 50%: the query parameter is well documented in the schema (Portuguese terms, literal accent matching), so the description need not repeat it. The limit parameter carries no description in either place, and the description does not explain that it caps the number of returned datasets, leaving one of two parameters underspecified.

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?

States a specific verb ('Search') and a named resource ('Portal de Dados Abertos de Curitiba catalogue'), and immediately clarifies its role as the entry point that feeds ids to dataset_files. An agent can distinguish it from dataset_files without opening either 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 chaining instruction 'pass an id to dataset_files' tells the agent what to do after this call and implicitly positions this tool as the discovery step. It never states the inverse condition (when not to search, e.g. when an id is already known), so guidance is clear but not complete.

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

Deploy Server

Other Tools