gentry.fr, le logement en France

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

Annotations already communicate that the operation is read-only, idempotent, and non-destructive functioning. The description adds value by specifying that it queries the BAN and returns coordinates plus INSEE code, and by flagging the arrondissement-vs-commune nuance. It does not discuss rate limits or pagination, but these are less material given the read-only hints.

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 the full functional description and the placement guidance with zero waste. The core purpose is front-loaded, and the caveat about INSEE/arrondissement codes is placed where it matters most—right after the primary call instruction.

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 geocoding look-up with no output schema, the description covers what the tool returns (coordinates and INSEE code), when to call it, and the critical Paris/Lyon/Marseille edge case. The input schema covers all parameter details, so nothing needed for correct invocation is missing.

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%, so the schema already documents both parameters and their valid ranges. The description reinforces the meaning of 'requete' ('adresse ou nom de commune') but adds no additional semantic detail beyond the schema, so the baseline 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 states a specific action ('Résout une adresse ou un nom de commune en coordonnées et en code INSEE') and names the data source (Base Adresse Nationale). It also distinguishes this tool from the sibling set by explaining that other tools operate on INSEE codes, which clarifies its unique role.

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?

It explicitly instructs when to invoke this tool: 'À appeler en premier quand la question porte sur un lieu'. It also explains why this is necessary—other tools work on INSEE codes, and Paris/Lyon/Marseille are represented by arrondissement codes—giving the agent a concrete decision rule.

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

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

Beyond the read-only, idempotent, and open-world annotations, the description adds behavior: it matches by meaning, accepts natural-language questions, searches the entire site, and returns pages with their addresses. This gives a useful picture of what the tool does without contradicting 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?

Three sentences, all substantive: the scope and mechanism, realistic usage examples, and a concrete invocation guideline. No filler or redundancy.

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?

The description is sufficient for a simple two-parameter read-only search tool. It explains what the tool returns, how the question should be phrased, and when to use it. The absence of an output schema is partially mitigated by the mention that pages and addresses are returned.

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 schema already documents both parameters. The description reinforces that the question is in plain language and that results are pages, but it does not add significant detail beyond the schema.

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-resource pair: search by meaning across all of gentry.fr and return relevant pages with their address. It also distinguishes itself from sibling tools by emphasizing semantic search over exact address lookup, which separates it from cherche_adresse.

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?

It explicitly states when to use this tool first: when uncertain whether gentry covers a topic, before concluding the data does not exist. It does not name alternatives explicitly, but the guidance is clear enough for routing.

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

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

Annotations already mark the tool as read-only and idempotent, so the description does not need to repeat that. It adds useful behavioral context: the comparison uses standardized dwelling types, returns specific metrics, and applies the annexe III CGI calculation method. 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?

The description is compact and front-loaded: it states the comparison purpose, the outputs, the calculation basis, and the primary use cases in three sentences. Every sentence adds information and there is no redundant 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?

Given there is no output schema, the description adequately explains what the tool returns: annual amount in euros, global voted rate, and ranking of least and most expensive communes. It also notes the standardized housing types and legal calculation basis, which is enough context for an agent to invoke 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 description coverage is 100%, so the parameters are already fully documented in the schema. The description adds no parameter-level detail, but it does not need to; the baseline of 3 is appropriate when the schema carries the parameter documentation burden.

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 uses a specific verb and resource: 'Compare la taxe foncière due dans les communes d'un département' and clearly states the outputs: annual amount, global rate, and ranking of cheapest/most expensive communes. This clearly differentiates it from siblings like fiche_commune, which is about a single commune.

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?

It gives explicit use cases: 'À utiliser pour « où la taxe foncière est-elle la moins chère », ou pour situer une commune face à ses voisines.' This is clear context for when the tool is appropriate, though it does not explicitly name alternatives or state when not to use it.

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

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

Annotations already mark it read-only, idempotent, and non-destructive, so the description's job is to add behavioral nuance. It explains the conditional output—which regime applies, and that the barème is returned only 'quand la commune en publie un'—plus the legal detail of the relocation cap. This goes well beyond the annotation fields.

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?

Three dense sentences: the first states the core purpose, the second explains the regimes, the third gives the barème condition and use cases. No filler, and the most important 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?

With no output schema, the description carries the burden of describing the return: whether the commune is covered, which of the three regimes applies, and the applicable barème when published. It is sufficient for an agent to invoke the tool correctly with the single commune parameter.

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% for the single 'commune' parameter, including examples of accepted formats. The description adds no new parameter-level detail, 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 uses a specific verb ('Dit si') and resource ('une commune applique l'encadrement des loyers'), then enumerates the three distinct regimes and the barème output. This clearly separates it from sibling tools like classement_taxe_fonciere or fiche_commune through its rent-control scope.

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 closing sentence explicitly states when to use it: 'pour toute question sur le montant légal d'un loyer, la relocation, ou le préavis réduit.' It gives clear context but does not explicitly name alternatives or exclusions, so it stops short of a 5.

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

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

The annotations already carry the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false), so the bar for additional disclosure is correctly lower. The description adds genuinely useful provenance by naming the public sources (DVF, Filosofi, DGFiP, INSEE) and framing the output as 'chiffres publiés', which tells an agent the data is official published data whose availability may depend on publication. Nothing here contradicts the 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?

The description is compact: a front-loaded enumeration of the returned figures followed by sources and use-case guidance. Every element earns its place, though the long list of outputs makes the sentence slightly dense rather than glossy.

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 a single parameter and no output schema, the description compensates by enumerating the return fields in detail (prices, rent, tax, population, neighbours), which is effectively the missing output schema. Edge cases like communes lacking published data or how to compare two communes with one accepted parameter are unaddressed, but those are minor given the simple, lookup-style tool and annotation-covered safety.

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%: the single parameter 'commune' already has a description ('Nom de commune, adresse ou code INSEE : « Rennes », « 35238 »'). The description adds no additional meaning beyond what the schema already states, so the baseline score of 3 applies. A sentence specifying accepted input formats would push this higher.

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 opens with a specific verb and resource ('Rend les chiffres publiés d'une commune française') and then enumerates the exact outputs: median property purchase price per square metre for houses and apartments, estimated listing rent, median standard of living, property tax rate, population and bordering communes. This precise itemization clearly distinguishes it from siblings such as 'cherche_adresse' or 'classement_taxe_fonciere'.

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 explicit use cases: 'À utiliser pour situer une commune, comparer deux communes ou répondre à « combien coûte l'immobilier à … »'. This is clear contextual guidance. However, it never names any sibling as the alternative for ranking or rent-control questions, so exclusion is left implicit, and 'comparer deux communes' sits awkwardly with a single-parameter schema.

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