Chaletiste

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

Annotations already establish that the tool is read-only and idempotent; the description adds meaningful behavior by stating that it returns the applied rule, the processing delay, and service-public.fr sources, and that it reminds users the local PLU can be stricter. 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?

Three sentences carry the purpose, decision factors, outputs, and an important caveat with no filler. The most important information is front-loaded and every sentence earns its place.

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?

Despite having no output schema, the description states what is returned (rule, delay, sources) and which inputs influence the result. It does not spell out the exact thresholds or fully formalize the output structure, but it is complete enough for an agent to select and 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 coverage is 100%, but the description adds decision logic beyond the schema: it explains that surface means the larger of footprint and floor area and links extension/PLU/protected-sector flags to the formalité outcome. This goes beyond the baseline of merely documenting parameter names.

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 precise verb, 'Indique la formalité d'urbanisme exigée...', names the resource ('chalet ou abri') and enumerates the possible outcomes ('aucune, dp, pc'). This clearly distinguishes it from sibling tools like get_chalet or search_chalets.

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 intended use is implied from the purpose: it answers what urban planning formality is required for a chalet/shelter. However, it never explicitly states when to call it versus alternatives and gives no exclusion or when-not-to-use guidance, so it stays at the implied-usage level.

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 declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral detail about what the comparison produces ('winners' per criterion), which goes beyond the structured annotations without contradicting them.

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 two sentences with no filler. The core action and constraints are front-loaded, and the long criterion list is compactly parenthesized rather than bloating the sentence.

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 single-parameter, read-only comparison tool with robust annotations, the description is complete. It specifies the model count, the criteria, the winner-selection behavior, and the user intent that should trigger it. No additional return-format detail is needed given the simple input and read-only nature.

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%: the only parameter 'ids' is described as 'Liste des id de modèles à comparer' with min and max constraints. The description reinforces the 2-to-6 limit and enumerates comparison fields, but it does not need to add meaning beyond the schema since the schema already fully documents the parameter.

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 ('Compare'), names the resource ('2 à 6 modèles côte à côte'), and enumerates the exact criteria compared (price, surface, insulation, etc.). It also clarifies the output behavior ('désigne pour chaque critère le modèle le mieux placé'), which clearly distinguishes it from siblings like get_chalet or search_chalets.

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 explicitly states when to use the tool: 'À utiliser quand l'utilisateur hésite entre plusieurs modèles ou demande « lequel choisir ».' This gives clear invocation context. It does not name exclusions or alternatives, 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?

Beyond the readOnly/idempotent annotations, the description discloses the exact outputs (total, low/high range, line-by-line detail, assumptions list) and the caveat that this is not a quote. It also surfaces key calculation rules like tax rates and the 5 m² exemption, adding substantial behavioral context.

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-organized: purpose first, then components, then outputs, then the caveat. Every clause carries information needed for correct invocation, and nothing is redundant with the schema.

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 an 8-parameter tool with no output schema, the description adequately explains what will be returned, the assumptions to cite, and the key tax calculation details. The remaining parameter semantics are fully covered by the schema, so nothing essential 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?

The schema already covers all 8 parameters with descriptions, so the baseline is 3. The description adds meaningful domain logic—tax rates, exemption thresholds, and how components combine—which helps the agent understand parameter relationships 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 opens with a specific verb and resource: 'Estime le budget total d'un projet pour un modèle donné' and enumerates the exact cost components. It also distinguishes itself from request_quote by explicitly stating 'pas un devis', making its purpose unambiguous relative to 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 clearly frames when to use the tool: to estimate a project budget for a given model. It provides an explicit exclusion ('pas un devis') and instructs the agent to tell the user the estimate is indicative, but it does not name alternative tools or give detailed when-not-to-use conditions.

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 declare readOnlyHint=true and destructiveHint=false, so the safety profile is clear. The description adds that the tool returns 'contenu complet' and the id format, which is useful context, but it does not detail the exact return structure or error behavior. Given the annotation coverage, a 3 is appropriate.

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, concise sentence that immediately states the action and includes the essential id format. No filler or repetition, with the key detail 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 fetch tool with one parameter, no output schema, and annotations covering safety, the description adequately explains purpose, id construction, and relationship to search. It does not describe the return fields, but given the direct tie to search results and the simple nature, this is a minor gap.

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 already describes the id as 'id renvoyé par search' (100% coverage), so the baseline is 3. The description enhances this by specifying the exact accepted formats ('chalet:<id>' or 'guide:<id>'), which is valuable guidance for constructing the parameter.

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 full content of a search result, specifies the id format ('chalet:<id>' or 'guide:<id>'), and ties it to the search tool. This precisely distinguishes it from siblings like get_chalet or get_guide, which likely target a single type directly.

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 usage after a search by mentioning 'résultat de search' and the id format, but it does not explicitly state when not to use it or compare it with alternatives like get_chalet and get_guide. Guidance is present but minimal.

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?

Goes well beyond the annotations by disclosing the AI-plus-rule-fallback extraction, deterministic ranking, return shape (criteria/understood, 6–12 models with 2–3 factual reasons, all-in budget estimate, relaxed criteria when empty, warnings with guide links), and a hard rate limit of 20 descriptions per day.

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?

Front-loads the input instruction, then the processing, return payload, a concrete example, the relaunch path, and the rate limit. Dense but every clause carries information; slightly long, yet 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 carries the return-value burden and does so fully: it enumerates criteria, understood, model count, reasons, budget estimate, relaxed criteria, and warnings. Rate limits and the relaunch mechanism are also covered, leaving nothing an agent needs to call it 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, but the description adds real meaning: criteria is the no-AI relaunch path (pass back a modified criteria object) and description is the natural-language project capped at 600 characters. This clarifies intent beyond the field names.

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 mechanism: takes a one-sentence natural-language project description, extracts criteria via AI with rule fallback, and deterministically ranks the 553-model catalogue. This clearly separates it from search_chalets or find_chalets_from_photo, though it never names those siblings explicitly.

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 prescribes the input format (a French sentence covering terrain, surface, budget, usage, deadline, assembly, region) and explains how to relaunch without AI via a modified criteria object, so usage is implied. But it never states when to prefer this over search_chalets or find_chalets_from_photo, and no exclusions are given.

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 annotations, it discloses substantial behavior: the AI-described attributes (type, surface, roof, terrace, construction, style, readable brand), the return shape (a 'best' match with a claim of recognition, plus 6-9 alternative proposals with cheaper/larger/faster angles), the privacy guarantee that no image is retained, and a concrete rate limit of 10 analyses per day. This is exactly the kind of operational context annotations cannot carry.

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?

Front-loaded with the required input and its constraints, then the processing and return behavior, then privacy and rate limits. It is a dense single paragraph but each clause carries information; only the phantom image_type reference is wasted/misdirecting text.

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 properly explains what comes back (best match plus 6-9 alternatives) and covers input constraints, privacy, and rate limits. The only completeness defect is the reference to a non-existent image_type parameter, which is inconsistent with the schema it ships with.

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 already 100%, so the schema documents image_url on its own; the description usefully adds format and 5 MB size limits. However, it references an 'image_type' value ('Si la photo montre un terrain, image_type vaut terrain') for a parameter that does not exist in the schema, which is misleading given additionalProperties=false and could cause a failed call.

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 verb+resource: take a photo URL, have AI describe the chalet, and return the closest catalog model plus 6-9 alternatives. This clearly differentiates it from siblings like find_chalets or search_chalets, which work from text/criteria rather than an image.

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 trigger is explicit and contextual: the user is showing a photo of a chalet ('une photo de chalet vue par l'utilisateur'), and the input constraints (public https URL, JPEG/PNG/WebP, 5 MB max) define when it can be called. It does not name alternatives such as find_chalets or compare_chalets, so the routing guidance stops short of full when-not instruction.

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?

Les annotations couvrent déjà la lecture seule, l'idempotence et la non-destructivité. La description ajoute utilement le périmètre détaillé du retour, les champs couverts et la présence de trois modèles similaires, ce qui va au-delà des 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?

La description tient en une phrase et chaque élément apporte une information utile, notamment la longue énumération des champs qui compense l'absence de schéma de sortie. La phrase d'usage est bien placée en fin, mais l'énumération rend l'ensemble un peu dense.

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?

En l'absence de schéma de sortie, la description liste de façon détaillée ce que renvoie l'outil et précise quand l'utiliser. Il manque seulement le comportement en cas d'identifiant inconnu ou des précisions sur d'éventuels frais, mais l'essentiel est couvert.

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?

Le schéma documente déjà l'unique paramètre id avec un exemple concret, soit une couverture de 100 %. La description ajoute seulement que l'id est obtenu via search_chalets, ce qui est un léger complément mais ne change pas le niveau de base.

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?

La description précise un verbe concret (« renvoie la fiche complète d'un modèle »), la ressource visée (un chalet via son id) et le contenu exact du retour. Elle distingue l'outil de search_chalets en indiquant que l'id provient de celui-ci.

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?

La description donne un contexte d'utilisation clair : « À utiliser avant de recommander un modèle précis ou de répondre à une question de détail ». Elle rattache aussi l'obtention de l'id à search_chalets, mais ne nomme pas explicitement d'alternative à éviter.

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 declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavioral context: the response structure (answer phrase, FAQ, dated sources) and the default-on full markdown body controlled by the full flag.

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, zero filler: the return payload is front-loaded before the usage condition. Every clause carries information an agent needs.

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 read-only lookup with no output schema, the description covers what the tool returns, how the full flag changes the payload, and when to reach for it instead of a model-specific tool. Nothing needed to invoke it correctly 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%, and the schema already documents both id (pointing to list_guides) and full with its true default. The description restates the full=true default and clarifies that it yields the complete markdown text, which is a marginal addition over the schema, so baseline 3 applies.

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 (Renvoie) and resource (un guide) and enumerates exactly what comes back: phrase-réponse, FAQ, sources datées, plus the markdown body when full is set. That level of output scoping lets an agent distinguish it from list_guides (enumeration) and get_chalet (a specific model) 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.

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

"À utiliser pour les questions de réglementation, de prix, de technique ou de budget qui dépassent un modèle précis" gives a clear trigger condition and implicitly routes single-model questions to get_chalet. No sibling is named explicitly, so it falls just short of an explicit when-not statement.

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 cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds genuine behavioral value by disclosing the return shape: 30 guides, each with a sourced one-sentence answer plus its FAQ, and that the payload is deliberately lighter than a full guide fetch.

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 front-loaded sentence that leads with the verb and the count, then the payload description. The topic enumeration is long but earns its place by revealing scope; only minor trimming would be possible without losing signal.

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 parameters and no output schema, the description carries the burden of explaining what comes back, and it does: count, per-item structure, and the practical consequence (often sufficient without the full guide). Minor gaps remain around whether the list is static or refreshed, but nothing needed to call it correctly 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?

The tool takes zero parameters, so per the rubric the baseline is 4. There is no parameter syntax or filtering to explain, and the description correctly focuses on output rather than inputs.

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 ('Liste') and resource ('les 30 guides de Chaletiste'), then enumerates the covered topics so the agent can judge coverage at a glance. It implicitly contrasts with sibling get_guide by noting it is 'souvent suffisant pour répondre sans charger le guide complet.'

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 clause gives a clear usage heuristic — use this summary listing first because it is often enough to answer without loading the full guide, which routes against get_guide. It stops short of an explicit exclusion (e.g., when you must load the full guide anyway), but the context is strong and actionable.

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 description discloses the flow: the request is relayed to a seller or installer who recontacts the user, the tool requires explicit consent, and dry_run avoids sending. It also notes the tool is free and non-binding, and clarifies that Chaletiste does not sell chalets. This adds meaningful context beyond the annotations, which already flag non-read-only and open-world behavior.

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 moderately long but each sentence earns its place: purpose, consent conditions, dry_run, and cost/free nature. It is front-loaded with the core action and avoids fluff. Slightly verbose due to the repeated emphasis on consent, but still appropriately concise for a safety-sensitive tool.

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 the tool has 10 parameters, no output schema, and a non-read-only action, the description covers essential context: the process flow, prerequisites, dry_run option, and non-binding nature. It does not detail the exact response format, but for a side-effect action this is acceptable. Could elaborate on what happens if dry_run is false, but the overall picture is complete enough.

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 all parameters are self-documented. The description reinforces the consent requirement and dry_run usage but does not add new per-parameter semantics beyond what the schema already provides. It meets the baseline but does not exceed it.

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 ('Transmet une demande de devis pour un modèle'), identifies the resource (a model), and clarifies the mediation role of Chaletiste. It clearly distinguishes this from sibling tools (search, compare, check_permit) by focusing on the quote request action.

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?

Explicitly states when to call the tool: only if the human user explicitly asked, provided their coordinates, and accepted their transmission. It also specifies that without consent the tool must not be called, and recommends dry_run for validation. This is strong, practical usage guidance.

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 declare the tool read-only, idempotent, and non-destructive. The description adds beyond that by revealing the result is only metadata and that actual content requires a separate fetch call. This is useful behavioral context that the annotations don't provide, so the description earns a strong score.

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 three short sentences: the first states what it does, the second gives the return format and next step, and the third names the alternative. It is front-loaded with the most critical information and contains zero filler, making it concise and efficient.

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 one-parameter search tool with no output schema, the description conveys everything needed: the resource scope, result fields, and the follow-up action (fetch). It also handles the decision point with search_chalets. The lack of pagination details is negligible for such a simple returned list.

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 schema already describes the single parameter as a natural language query or keywords, giving 100% coverage. The description adds no additional insight about the parameter itself; it focuses on output and follow-up steps. Per the rule, baseline 3 applies because schema covers the parameter fully.

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 performs full-text search on chalets and guides, and specifies the exact return format (id, title, url). It explicitly differentiates from search_chalets by naming it as the filtered alternative, leaving no ambiguity about the tool's 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?

It provides direct instructions: use fetch with the id to get content, and prefer search_chalets for filtered queries. This gives explicit when-to-use guidance and names the sibling tool that replaces it for different needs, so the agent knows exactly how to route its request.

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 declare readOnly/idempotent/non-destructive/closed-world, but the description adds real behavioral context: assembly_estimated=true means a Chaletiste estimate rather than a manufacturer figure, models lacking the filtered data are excluded, each result carries an observed price with its survey date, and the answer must cite Chaletiste and the price date. It does not mention pagination or result caps beyond the schema's 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?

One dense but well-ordered paragraph: purpose and corpus size first, then filters, then the shape of a result, then usage examples, exclusion rule and citation requirement. Long, yet each sentence carries information; only the category enumeration borders on redundancy with the schema enum.

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 13 optional parameters and no output schema, the description takes on the full burden and delivers: it documents the returned fields (id, prix TTC + date, surface, épaisseur, temps de montage, délai, formalité d'urbanisme) and the meaning of the urbanisme codes, which is exactly what an agent needs to consume results 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 every parameter is already documented in the schema. The description only restates the filter axes (budget, surface, paroi thickness, délai de livraison, temps de montage) and does not add syntax, unit or interaction detail beyond what the schema gives, so the baseline 3 applies.

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 ("Cherche") and resource (553 chalets en bois en kit vendus en France), enumerates the covered product families and the filter dimensions. It names downstream siblings (get_chalet, compare_chalets, estimate_total_budget, request_quote) but never differentiates itself from the closest siblings find_chalets, find_chalets_from_photo or search, so an agent still has to guess which search entry point to use.

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?

Gives explicit trigger queries ("quel chalet de 20 m² à moins de 6 000 €", "abri livré en moins de 3 semaines") and a clear exclusion rule (models missing the filtered field are dropped). It stops short of naming the alternative tool to use when this one is not appropriate, so the routing against find_chalets/search remains implicit.

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