Parcelas catastrales de CABA y AMBA (Buenos Aires) desde tu asistente de IA (MCP remoto).
Scored across 5 tools
The three search tools are cleanly separated by input axis (point, cadastral identifier, area), and cobertura_y_fuentes is clearly metadata. The main soft spot is ficha_parcela, whose inputs and relationship to parcela_por_nomenclatura (both plausibly take a cadastral ID to return a record) are not distinguished in the descriptions.
All names are Spanish snake_case and consistently resource-first, with a recognizable 'parcela/parcelas' stem across four tools. The patterns vary slightly (noun_por_X, noun_en_area, noun_y_fuentes) rather than following a single verb_noun template, but the set reads predictably.
Five tools is a tight, focused surface: three lookup modes, one record fetch, and one coverage/metadata endpoint. It is on the lean side — no update/write operations — but nothing feels redundant or missing for a read-only cadastral lookup service.
The lookup lifecycle is well covered: locate parcels by point, identifier, or area, then fetch the full record, plus coverage/attribution metadata. Minor gaps exist (no address-based search, no bulk/batch or geometry export), but core workflows are achievable.
Devuelve cobertura disponible y atribuciones. Get available coverage and sources.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, covering the safety profile. Beyond that, the description adds nothing: no indication of what the returned coverage/attribution structure represents, whether results are static reference data, or roughly how large the response is. For a zero-parameter catalog/meta tool, more framing about the returned reference data would be valuable.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence front-loading the action and resource, with a parallel English rendering. It is short and waste-free, though the bilingual duplicate essentially repeats the same content and the input schema's own description, so it carries little added information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
An output schema exists, so return values need not be explained, and there are no parameters or nesting to document. The remaining gap is conceptual: what "cobertura" and "atribuciones" actually contain and why an agent would call this before a parcel query. That leaves the definition minimally viable rather than complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool takes zero parameters, so there is no parameter semantics for the description to explain. This hits the baseline of 4 for parameter-free tools; nothing is missing on this dimension.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a verb and resource ("Devuelve cobertura disponible y atribuciones" / "Get available coverage and sources"), so the agent knows it is a read of coverage metadata. However, "cobertura" is left undefined — it is unclear whether it means geographic data coverage, dataset extent, or licensing/attribution info — and nothing distinguishes it from the sibling parcel-lookup tools. It reads close to a restatement of the title "Cobertura y fuentes".
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no guidance on when to call this versus ficha_parcela, parcela_por_coordenada, parcela_por_nomenclatura, or parcelas_en_area, and no stated prerequisites or follow-up flow. The agent must infer from the name alone that this is a metadata/scope-check tool rather than a parcel query.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Devuelve la ficha de una parcela CABA o PBA. Get a CABA or PBA parcel record.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | ||
| incluir_geometria | No |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=false), so the bar is low, but the description adds nothing beyond them: no note on what the ficha contains, whether missing parcels error or return empty, or what the geometry flag changes in the payload.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
It is short and front-loaded, but it is the same sentence stated twice (Spanish then English), which doubles length without adding information rather than spending that space on the missing id/geometry semantics.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
An output schema exists, so return values needn't be described, but for a two-parameter lookup tool sitting among three near-identical siblings, the absence of param format details and sibling differentiation leaves the definition materially incomplete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
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 it does not. The 'id' parameter's expected format (CABA vs PBA identifier shapes) is unexplained, and 'incluir_geometria' — a toggle with real output-size implications — is not mentioned anywhere.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description names a specific verb ('Devuelve') and resource ('ficha de una parcela'), and scopes it to CABA or PBA. However, it never states that lookup is keyed on an 'id', nor does it distinguish this from siblings like parcela_por_nomenclatura or parcela_por_coordenada that fetch the same record via different keys.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no when-to-use guidance at all. With four sibling tools that all surface parcel data, the agent is left to infer that this one is for direct id lookup; nothing in the text confirms or excludes that.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Busca parcelas en un punto de CABA o PBA. Find CABA or PBA parcels.
| Name | Required | Description | Default |
|---|---|---|---|
| lat | Yes | ||
| lon | Yes | ||
| incluir_geometria | No |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so the description's added value is what matters, and it adds essentially nothing: no statement about what happens when the point falls outside CABA/PBA, whether one or multiple parcels may be returned, or whether the result is a best-match vs exhaustive lookup. For a spatial lookup where boundary/edge cases are the main behavioral risk, that is a real gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short sentences, front-loaded with the verb and the scope, with zero padding. The English sentence is a near-verbatim translation that adds no new information, though it can aid retrieval, so it is not pure waste.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
An output schema exists, so return values needn't be described, but for a geospatial point-query tool the description omits coordinate format, out-of-coverage behavior, and the meaning of the geometry flag. Given three parameters, none documented, and a hard scope boundary, the definition is too thin to call confidently in edge cases.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% across three parameters, and the description compensates for none of them: the coordinate reference system/units for lat and lon are unstated, and incluir_geometria (default false) is never explained — an agent cannot tell that it controls whether geometry is returned. Only the field names themselves carry meaning.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ("Busca parcelas") plus the lookup mode ("en un punto") and the geographic scope (CABA or PBA), which lets an agent separate it from parcelas_en_area and parcela_por_nomenclatura by inference. It never names those siblings explicitly, so the differentiation is implicit rather than stated.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage is only implied: an agent can infer this is the tool for a lat/lon point lookup, and the CABA/PBA constraint hints at a coverage limit. There is no explicit when-to-use, no when-not (e.g. don't use for areas or nomenclatures), and no routing to the sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Busca SMP CABA, CCA PBA o partida y partido. Find parcels by cadastral identifier.
| Name | Required | Description | Default |
|---|---|---|---|
| smp | No | ||
| partida | No | ||
| partido | No | ||
| jurisdiccion | No | CABA | |
| nomenclatura | No | ||
| incluir_geometria | No |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds nothing beyond that: it does not say whether identifiers can be combined, whether at least one is required, what happens with defaults, or what the response contains, leaving the agent to guess about a lookup with six optional inputs.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Only two sentences, so nothing is bloated, but they are near-duplicate Spanish/English restatements rather than complementary information. The budget is small but the second sentence adds little beyond translation.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With six optional parameters, zero schema descriptions and a default jurisdiction, the agent needs to know how the identifier fields relate (mutually exclusive vs combinable) and which one to prefer. An output schema exists so return values need no explanation, but the input-side ambiguity is significant for a tool whose whole job is disambiguating identifier formats.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must carry the burden, and it only partially does: it names SMP, CCA, partida and partido but never explains 'nomenclatura' (the tool's own name), the CABA/PBA jurisdiction switch or 'incluir_geometria'. The overlap between smp and nomenclatura remains unexplained.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description names a specific verb ('Busca'/'Find') and resource ('parcels'/'parcela') and scopes it to cadastral identifiers (SMP, CCA, partida/partido), which lets an agent distinguish it from parcela_por_coordenada and parcelas_en_area. It does not explicitly name those siblings, but the identifier-based framing makes the distinction inferable.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no guidance on when to choose this tool over parcela_por_coordenada, parcelas_en_area or ficha_parcela, nor any prerequisite or exclusion. Usage is only implied by the phrase 'by cadastral identifier'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Busca parcelas en hasta 1 km², lados de hasta 2 km. Find parcels in a small area.
| Name | Required | Description | Default |
|---|---|---|---|
| cursor | No | ||
| limite | No | ||
| max_lat | Yes | ||
| max_lon | Yes | ||
| min_lat | Yes | ||
| min_lon | Yes |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered; the description's real contribution is the hard area/side-length limit, which is a genuine behavioral constraint absent from the schema (no max on coordinates). It says nothing about pagination behavior, coordinate reference system, or what happens when the rectangle exceeds the limit.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short sentences with the key constraint front-loaded. The English sentence is largely a restatement of the Spanish one, so it is redundant for anyone reading both, though harmless for cross-lingual routing.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
An output schema exists, so return values need not be described, and the core purpose plus area cap are covered. For a 6-parameter tool with zero schema documentation, however, the absence of any guidance on cursor/limite pagination and coordinate ordering leaves real gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% for all six parameters, so the description must carry the load; it only partially does, clarifying the spatial extent limit but never explaining the cursor/limite pagination parameters or that min_lon/min_lat/max_lon/max_lat are degrees forming a bounding box.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ('Busca parcelas') plus a concrete spatial scope ('hasta 1 km², lados de hasta 2 km'), which distinguishes it from the point-lookup and cadastral-code siblings without naming them. The only weakness is that the contrast with parcela_por_coordenada and parcela_por_nomenclatura is left implicit.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The size cap ('hasta 1 km²', 'lados de hasta 2 km') implies the intended use case – small-area searching rather than a whole municipality – but there is no explicit when-to-use, when-not-to-use, or named alternative among the four siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
cobertura_y_fuentes1 field changedInput schema / descriptionPrevious value: -"Devuelve cobertura CABA y atribuciones. Get CABA coverage and sources."New value: +"Devuelve cobertura disponible y atribuciones. Get available coverage and sources."ficha_parcela1 field changedInput schema / descriptionPrevious value: -"Devuelve la ficha de una parcela de CABA. Get a CABA parcel record."New value: +"Devuelve la ficha de una parcela CABA o PBA. Get a CABA or PBA parcel record."parcela_por_coordenada1 field changedInput schema / descriptionPrevious value: -"Busca parcelas en un punto de CABA. Find parcels at a point in CABA."New value: +"Busca parcelas en un punto de CABA o PBA. Find CABA or PBA parcels."parcela_por_nomenclatura5 fields changedInput schema / descriptionPrevious value: -"Busca un SMP de CABA con o sin espacios. Find a CABA parcel by SMP."New value: +"Busca SMP CABA, CCA PBA o partida y partido. Find parcels by cadastral identifier."Input schema / properties / jurisdiccion / constRemoved value: -"CABA"Input schema / properties / jurisdiccion / enumAdded value: +[
+ "CABA",
+ "PBA"
+]Input schema / properties / partidaAdded value: +{
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "title": "Partida"
+}Input schema / properties / partidoAdded value: +{
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "title": "Partido"
+}cobertura_y_fuentesficha_parcelaparcela_por_coordenadaparcela_por_nomenclaturaparcelas_en_areaMCP server for Japan geodata: cadastral lot numbers (chiban) and reverse geocoding, for AI agents.
Données foncières du Québec pour assistants IA (MCP) · Québec land data for AI assistants
Italian cadastre for AI agents: 85M parcels, geocoding, OMI values, risk layers.
Flat-rate US property/parcel search & CSV export for AI agents via MCP.
Add one secure layer between your agents and this server.
