French land-use plans (PLU): what a zone or a street allows, cited at the article. No key.
Scored across 4 tools
Each tool has a clearly distinct purpose: one for permit document requirements, one for street-specific urbanism rules, one for zone-level rules, and one for keyword search. The street and zone tools overlap in content, but they operate on different inputs and provide different levels of detail, so confusion is unlikely.
All tool names follow a consistent verb_noun pattern, using 'get_' or 'search_' as the verb, and all include 'french' to indicate the domain. The nouns are descriptive and parallel in structure, making the set predictable and easy to scan.
With only 4 tools, the server is tightly scoped to French urbanism queries. Each tool addresses a core need—permit pieces, street rules, zone rules, and regulation search—without redundancy or bloat, which is appropriate for this specialized domain.
The tools cover the essential workflow: determining required documents, understanding rules for a street or zone, and searching regulation text. There's no explicit way to list zones or streets, but the existing tools assume the user provides those inputs, which is reasonable for the apparent scope.
Les pieces a joindre a une demande de permis de construire pour une maison individuelle en France (formulaire Cerfa 13406*15), en distinguant celles qui sont exigees partout de celles que le terrain declenche : sismicite, plan de prevention des risques, monument historique. Faits lus au centre de la commune, pas a une adresse.
| Name | Required | Description | Default |
|---|---|---|---|
| code_insee | Yes | Code INSEE de la commune, cinq caracteres, par exemple 31395 (Muret). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate read-only, idempotent, open-world, non-destructive behavior. The description adds meaningful behavioral detail: output distinguishes universally required pieces from terrain-triggered ones, and facts are based on commune center rather than a specific address. This exceeds annotation coverage.
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?
A single, dense sentence carries the full purpose, scope, output categorization, and spatial limitation without redundancy. Every clause earns its place, and key information is front-loaded.
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?
For a simple one-parameter, read-only tool with no output schema, the description covers purpose, scope, granularity, and categories of results. It does not enumerate the actual pieces, but that is not required for tool selection; the description is reasonably complete for invoking the tool correctly.
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 coverage is 100%, so the baseline is 3. The description adds value by explaining that code_insee determines commune-level triggers like sismicite, risk prevention plans, and historic monuments, and clarifies spatial resolution (commune center). This goes beyond the schema's format-only description.
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 resource ('pieces a joindre a une demande de permis de construire pour une maison individuelle'), specifies the Cerfa form, and distinguishes universal requirements from terrain-triggered ones. This clearly differentiates it from the urbanism-rule siblings.
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 description makes the context clear: it is for an individual house building permit in France, with results read at commune center, not at an address. It implicitly excludes address-level use but does not explicitly name alternatives or state when-not-to-use relative 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.
La zone du plan local d'urbanisme au droit d'une rue francaise et ce que le reglement en dit : les regles du chapitre avec les cas propres au secteur en avant, ce que le plan graphique impose ici, les autres zones que la voie longe a 120 m, les prescriptions et servitudes dessinees autour, les pieces du permis que le terrain declenche. Meme texte que le jumeau .md de la page de rue. Avec le numero de rue : le terrain de ce numero - ses parcelles cadastrales reunies, ce qui les reunit, la zone lue a son contour et les chiffres du reglement ramenes a lui.
| Name | Required | Description | Default |
|---|---|---|---|
| voie | Yes | Nom de la voie en toutes lettres, par exemple « avenue Jacques Douzans ». | |
| numero | No | Le numero dans la voie, par exemple « 22 » ou « 12 bis » : rend le terrain de ce numero. Sans lui, la voie au point. | |
| code_insee | Yes | Code INSEE de la commune, cinq caracteres, par exemple 31395 (Muret). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations indicate readOnly, openWorld, idempotent, and non-destructive hints, which the description aligns with. However, the description does not add behavioral context beyond these hints; it does not mention output format, whether the tool may return partial data for incomplete addresses, or that it matches the 'twin .md' text of the street page. The openWorldHint suggests data may change, but the description does not explicitly warn about dynamic data.
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 concise but dense, packed with details in two long sentences. It front-loads the primary purpose and then expands on optional scoping. However, the second sentence is somewhat run-on and could be clearer with better punctuation, but it remains efficient and informative.
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?
For a tool with no output schema (unknown return structure), the description could explain what the output looks like (e.g., text, structured data) and note that it mirrors the street page's .md format. It also doesn't clarify how the 120m radius is used or how far the 'prescriptions' extend. However, given the tool's complexity, the description covers many aspects (zone, reglement, plan, prescriptions, pieces), but lacks explicit guidance on output and potential 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?
The input schema provides excellent descriptions for 'voie' and 'code_insee', but the description adds meaning for 'numero' by explaining that it scopes to a specific plot and aggregates cadastral parcels. For 'voie', the description reiterates the schema's example of 'avenue Jacques Douzans', but reinforces the requirement for full spelling. Since schema coverage is 100%, the description's added value on parameters is moderate, but it does clarify the optional 'numero' behavior.
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 clearly states the tool returns the urban planning rules for a French street, including the zone, graphical plan constraints, nearby zones at 120m, prescriptions, and permit pieces. It distinguishes itself from siblings by mentioning the 'rue' context and the optional street number that scopes to a specific plot.
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 description explains that without a street number, the tool returns the rules for the street point, and with a number it returns the specific plot's rules. It implies a use case (getting urbanism rules for a street) but does not explicitly contrast with sibling tools like get_french_urbanism_zone_rules or search_french_urbanism_regulation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Ce qu'une zone d'un plan local d'urbanisme francais autorise. Quand la commune est compilee, les regles en clair - hauteur, emprise, reculs, stationnement, espaces verts - chacune avec sa valeur, la condition qui la declenche et la phrase du reglement qui la porte ; puis le texte integral des articles de la zone. Meme texte que le jumeau .md de la page de zone. Un document qui ne suit pas la numerotation attendue rend zero article, et l'outil le dit plutot que de deviner.
| Name | Required | Description | Default |
|---|---|---|---|
| zone | Yes | Code de zone du plan local d'urbanisme, par exemple UA, UB, AU, A ou N. | |
| code_insee | Yes | Code INSEE de la commune, cinq caracteres, par exemple 31395 (Muret). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already declare the tool read-only, idempotent, and non-destructive. The description adds valuable behavioral context by describing the output structure, the equivalence with the .md twin, and the failure mode where a document with unexpected numbering returns zero articles and says so instead of guessing.
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 dense but well-structured: purpose first, then output composition, then the twin-document equivalence, then the failure behavior. Every sentence adds distinct useful information with no filler.
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 no output schema, the description adequately explains what the agent will receive: clear rules with value, condition, and regulation text, followed by full articles. It also covers an important edge case. It does not describe behavior when the commune is not compiled, but overall it is sufficiently complete for a simple two-parameter read-only tool.
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 100%, with both code_insee and zone fully documented including examples and a pattern. The description adds domain context about rule categories, but no parameter-level semantic detail beyond what the schema already provides.
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 opening sentence clearly states that the tool returns what a zone of a French PLU authorizes, with a specific verb and resource. It is obviously zone-scoped and distinguishes itself from street-level or search siblings, though it does not explicitly name those alternatives.
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 description implies when to use the tool: when you need zone-level urbanism rules and the commune is compiled. However, it does not explicitly contrast this tool with get_french_urbanism_rules_for_street or search_french_urbanism_regulation, so the routing guidance is left mostly to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Cherche des mots dans le texte du reglement d'urbanisme d'une commune francaise et rend les articles qui les contiennent, avec leur zone et leur numero. Utile quand on ne sait pas dans quel article une regle se trouve : cloture, piscine, toiture, stationnement.
| Name | Required | Description | Default |
|---|---|---|---|
| mots | Yes | Les mots a chercher, par exemple « hauteur ». | |
| code_insee | Yes | Code INSEE de la commune, cinq caracteres, par exemple 31395 (Muret). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, and non-destructive behavior, so the description does not need to restate safety. It adds useful behavioral detail beyond annotations: it performs keyword search over regulation text and returns the containing articles with zone and number. No contradiction with annotations.
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 sentences carry all essential information: what the tool does, what it returns, and when to use it. The examples are compact and useful, with no redundant phrasing.
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?
For a simple read-only search tool with two parameters, a complete schema, and rich annotations, the description is sufficient. It explains the search target, the return shape, and the typical use case. There is no output schema, so the description's mention of returned articles, zone, and number fills that gap well.
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 coverage is 100%, with both parameters already well described. The description reinforces the meaning of 'mots' through examples but adds little semantic value beyond the schema, so the baseline of 3 is appropriate.
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 clearly states a specific verb ('Cherche des mots'), the resource (the text of a French commune's urbanism regulation), and the output (articles with their zone and number). This makes it easy to distinguish from the sibling getter tools, which target permits, street rules, or zone rules rather than full-text keyword search.
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 description gives a clear use case: 'Utile quand on ne sait pas dans quel article une regle se trouve', followed by concrete examples like cloture, piscine, toiture, stationnement. It does not explicitly name sibling tools or state when not to use them, but the intended context is clear.
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.
get_french_urbanism_rules_for_street1 field changedInput schema / properties / numeroAdded value: +{
+ "description": "Le numero dans la voie, par exemple « 22 » ou « 12 bis » : rend le terrain de ce numero. Sans lui, la voie au point.",
+ "type": "string"
+}get_french_building_permit_piecesget_french_urbanism_rules_for_streetget_french_urbanism_zone_rulessearch_french_urbanism_regulationAustralian planning data for ~455 councils, 7 states — clause-cited, confidence-tagged.
A French address, all public facts: parcel, zoning, risks, permits, sales, energy labels. No key.
French open data: communes, parcels, risks, property sales, water, crime, planning.
French real estate data: cadastre, DVF sales, DPE energy ratings, price estimates, parcel context
Add one secure layer between your agents and this server.
