Skip to main content
Glama

flatin.pt — Portuguese homes: taxes, construction, new-builds

by pt.flatin
OverviewDiscussionsAdmin

Look up the IMI rate of a municipality

imi_rate
Read-onlyIdempotent

Use this when only the yearly IMI (municipal property tax) rate of one Portuguese municipality is needed, by name or code, with its history by year. Do not use it for the yearly amount on a VPT (imi_annual_cost) or for several municipalities side by side (compare_municipalities). Rates: Autoridade Tributária portal, all 308 municipalities. Where the rate is set per parish, the answer says so instead of giving a number.

Input Schema

NameRequiredDescriptionDefault
municipalityYesMunicipality name (Porto, Lisboa or Lisbon, Vila Nova de Gaia) or its four-digit code (1312)

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / municipality / examples
      Added value: +[
+  "Porto",
+  "Lisbon",
+  "1312"
+]
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "anyOf": [
+    {
+      "properties": {
+        "attribution": {
+          "type": "object"
+        },
+        "codigo": {
+          "description": "Four-digit Tax Authority code",
+          "type": "string"
+        },
+        "distrito": {
+          "type": "string"
+        },
+        "history": {
+          "type": "object"
+        },
+        "municipality": {
+          "type": "string"
+        },
+        "rural": {
+          "type": "object"
+        },
+        "urban": {
+          "type": "object"
+        },
+        "year": {
+          "type": "integer"
+        }
+      },
+      "required": [
+        "codigo",
+        "municipality",
+        "distrito",
+        "urban",
+        "rural",
+        "year",
+        "history",
+        "attribution"
+      ],
+      "type": "object"
+    },
+    {
+      "description": "Refusal (isError: true). `error` is a machine code (not_found, bad_*, tool_failed…), `message` says what to fix.",
+      "properties": {
+        "error": {
+          "type": "string"
+        },
+        "message": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "error",
+        "message"
+      ],
+      "type": "object"
+    }
+  ],
+  "description": "Success, or a refusal with an error code. Units: *_cents euro cents, *_eur euros, *_eur_m2 euros per m², *_pct and percent in percent.",
+  "type": "object"
+}
  2. Changed1 schema field changed
    • changedInput schema / properties / municipality / description
      Previous value: -"Municipality name in Portuguese (Porto, Lisboa, Vila Nova de Gaia) or its four-digit code (1312)"New value: +"Municipality name (Porto, Lisboa or Lisbon, Vila Nova de Gaia) or its four-digit code (1312)"
  3. Changed1 schema field changed
    • changedInput schema / properties / municipality / description
      Previous value: -"Municipality name (Porto, Vila Nova de Gaia) or its four-digit code (1312)"New value: +"Municipality name in Portuguese (Porto, Lisboa, Vila Nova de Gaia) or its four-digit code (1312)"
  4. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the readOnly/idempotent annotations, it discloses the data source (Autoridade Tributária), full coverage (all 308 municipalities), and an important edge case: per-parish rates return an explanation rather than a number. The output schema already covers return shape, so this is exactly the extra behavioral context that earns credit.

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 tight sentences, each with a distinct job: when to use, when not to use with named alternatives, then source/coverage/caveat. Front-loaded with the usage decision and zero filler.

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 single-parameter read tool with full annotations and an output schema, everything an agent needs is present: trigger condition, alternatives, data provenance, coverage, and the per-parish fallback behavior.

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 100% and the parameter already documents name-or-code with examples, so the schema does the heavy lifting. The description only restates 'by name or code' without adding matching tolerance, casing, or ambiguity handling beyond what the schema shows. Baseline 3 is appropriate.

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?

Specific verb and resource ('look up the IMI rate of one Portuguese municipality'), plus explicit scope (single municipality, history by year). It names the two sibling tools it is not, so an agent can distinguish it from imi_annual_cost and compare_municipalities 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 Guidelines5/5

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

States the triggering condition ('when only the yearly IMI rate ... of one municipality is needed') and two explicit exclusions mapped to the correct alternatives: imi_annual_cost for VPT amounts, compare_municipalities for side-by-side. Nothing is left to inference.

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

All flatin.pt — Portuguese homes: taxes, construction, new-builds 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