Frigolog HACCP — French Food Safety Compliance

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

With no annotations provided, the description carries the full burden. It discloses data provenance ('les prix viennent des grilles publiques des éditeurs'), flags unverified information ('ce qui n'est pas publié... est signalé comme tel'), and even reveals a conflict of interest ('Frigolog publie ce MCP'). This exceeds typical transparency expectations for a read-only comparison tool, though it does not explicitly state it causes no side effects.

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 front-loaded with the core purpose and then lists the compared solutions and criteria. It is bilingual, which adds some redundancy, but each sentence carries substantive information. It remains reasonably concise for the complexity involved, avoiding unnecessary 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?

Without an output schema, the description thoroughly explains what the tool returns: the list of solutions, all comparison fields (price, engagement, materials, AI features, IoT, support, 3-year cost, etc.), and the 'note_verification' field for sources and status. It also covers the optional parameter behavior and the data date (April 2026). This is comprehensive for a tool with a single optional 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?

The input schema already provides 100% coverage for the single 'solution' parameter, including all allowed values and behavior for present/absent. The description only repeats the parameter name ('Optional 'solution'') without adding new semantic details. Therefore, the baseline of 3 applies, as the schema does the heavy lifting.

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 'Renvoie un comparatif factuel des principales solutions logicielles HACCP disponibles sur le marché français', specifying the exact verb 'returns' and the resource (a factual comparison of HACCP software). It lists all seven solutions and the comparison criteria, making its purpose unmistakable. This distinguishes it from sibling tools that retrieve specific regulatory or safety data.

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 it evident when to use this tool: whenever the user needs a comparison of HACCP software on the French market. It also explains the optional 'solution' parameter for filtering to a single solution. However, it does not explicitly mention when not to use it or name alternative tools as substitutes, but the context is clear given the sibling tools' specific scopes.

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 details the structure of the output (immediate action, documentation, deadlines, etc.) and the optional filter. Since there are no annotations, the description carries the full burden and adequately conveys that this is a read-only information retrieval tool.

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 front-loaded with the purpose and structured with bullet points. However, the bilingual content (French and English) doubles the length unnecessarily, slightly reducing conciseness.

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 single optional parameter and no output schema, the description fully compensates by detailing the response structure for each non-conformity. It provides comprehensive context for an agent to invoke and interpret 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?

The input schema already provides a description of the optional 'type_non_conformite' parameter with valid values. The tool description repeats this information without adding new semantics, so it meets the baseline for 100% schema coverage.

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 regulatory corrective actions for 6 specific non-conformities in catering. It uses a specific verb ('retourne/returns') and resource ('actions correctives'), distinguishing it from sibling tools like 'get_haccp_temperatures' or 'get_regles_dlc'.

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 lists the 6 non-conformities and mentions an optional filter, implying when to use it. However, it does not explicitly state when not to use it or provide alternatives, though the sibling tools cover different domains.

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?

No annotations are provided, so the description carries full burden. It discloses dataset size, refresh cycle, coverage since April 2017, and parameter precedence (SIRET overrides others). This fully informs the agent of behavioral traits.

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 front-loaded with purpose and well-structured in two paragraphs plus an English version. While the bilingual repetition adds length, every sentence contributes useful information. Could be slightly more concise.

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 no output schema and no annotations, the description thoroughly covers search behavior, return fields, data source, and limitations. It leaves no critical gaps 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 baseline is 3. The description repeats some schema details (e.g., SIRET uniqueness, full-text search on nom) without adding significant new semantics. It provides minimal extra value 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 explicitly states the tool's purpose: searching for an establishment's Alim'confiance score. It lists specific return fields (score, date, SIRET, etc.) and distinguishes the search modes, making it clear what resource is accessed.

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 recommends using SIRET for direct searches and explains when to combine nom with code_postal or commune to disambiguate. It does not explicitly contrast with sibling tools like get_score_alimconfiance, but provides sufficient context for effective use.

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?

With no annotations provided, the description carries full burden. It thoroughly explains what the tool returns (names, sources, obligations, penalties) and the optional parameter. It does not mention rate limits or side effects, but as a read-only retrieval, the behavioral context is sufficiently conveyed.

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 well-structured with two paragraphs, front-loading the purpose. The list of allergens is somewhat lengthy but adds value. It is concise enough for an AI agent to parse quickly.

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 absence of an output schema, the description compensates by detailing the output content (names, sources, obligations, penalties). With one optional parameter fully documented, the description is complete for the tool's purpose.

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 a well-described parameter. The description adds context about the filter being optional and defaulting to all allergens, but this adds only marginal value beyond the schema. 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 explicitly states that the tool returns the list of 14 mandatory allergens under EU Regulation 1169/2011, including common names, sources, display obligations, and penalties. This clearly differentiates it from sibling tools that focus on other HACCP or food safety aspects.

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 indicates the tool is used to retrieve allergen information, with an optional filter. While it does not explicitly state when not to use it or mention alternatives, the context and sibling names make the usage context clear.

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?

Describes the logic (based on last-action dates) and outputs (due date, urgency, action). No annotations provided, so description carries full burden—does not explicitly state it's read-only or discuss authorization/rate limits; but does not hide destructive 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?

Two-language description is front-loaded with key action verb ('Retourne'), short sentences, no superfluous information. Every sentence adds value.

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 6 parameters and no output schema, the description adequately explains the expected output (urgency, due date, action) and the tool's automation purpose. Minor gap: could mention if it handles missing optional dates gracefully.

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%, and description adds business context (e.g., 'recyclage tous les X ans', 'fréquence moyenne des inspections') beyond the schema descriptions. Explicitly highlights required 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 it returns the calendar of upcoming HACCP obligations for an establishment, using specific dates. It distinguishes from sibling tools like 'get_score_alimconfiance' or 'get_risque_inspection' by focusing on a computed calendar of obligations.

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 designed for automation (weekly call and alert), and mentions required parameter. No explicit when-not-to-use or exclusion of siblings, but the use case is clear.

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?

No annotations are provided, so the description bears full responsibility. It details the checklist contents (visual checks, temperatures, stock, hygiene, documents) without mentioning side effects or permissions. Since it is a read-only retrieval, this level of transparency is adequate.

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 informative but includes both French and English text, making it longer than necessary. The core purpose is front-loaded, and every sentence adds value, but could be more streamlined by keeping one language.

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 absence of an output schema, the description adequately explains what the tool returns by listing categories and item count (from schema). It is complete enough for a checklist retrieval tool, though a more explicit return format would be helpful.

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% for the single optional parameter. The description explicitly states that the parameter adds trade-specific items, and the schema provides valid values and explains the default behavior. This adds clear meaning 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 clearly states 'Retourne la checklist complète de vérification à réaliser avant l'ouverture quotidienne d'un établissement alimentaire en France', which is a specific verb+resource. It is distinct from sibling tools that cover other aspects like allergens or corrective actions.

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 use for daily pre-opening checks but does not explicitly state when not to use it or compare with alternatives. The context suggests it is for routine morning checks, but lacks explicit usage boundaries.

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?

No annotations are provided, so the description must carry the full burden. It does not disclose behavioral traits such as authentication requirements, rate limits, error handling, or potential side effects. However, it does describe the output content (common base + specific documents) and filtering logic, which is moderately transparent for a read-only lookup tool.

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 presented in two languages (French and English), which is useful for a bilingual context. The key information is front-loaded. Minor repetition between languages could be streamlined, but overall it is concise and well-structured.

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 one optional parameter and no output schema, the description covers the purpose, filtering behavior, and output content adequately. It lacks information about data freshness or source, but this is not critical for a reference document list. The tool is simple enough that the description feels 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 single parameter 'type_etablissement' is fully covered in the input schema (100% coverage). The description adds significant value by explaining the outcome of providing vs. omitting the parameter, listing valid values, and clarifying that the result includes common plus specific documents when filtered. This goes well beyond the schema's basic 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 explicitly states the tool returns a list of documents requested by French DDPP inspectors during sanitary inspections, by establishment type. It clearly distinguishes from sibling tools like get_guide_bonnes_pratiques_secteur or get_plan_nettoyage_type, which focus on specific guidance or plans.

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 context (DDPP inspections, France) and mentions optional filtering by type_etablissement. However, it does not explicitly compare to siblings or state when not to use this tool. Given the variety of sibling tools, some guidance on when to choose this over related tools (e.g., get_guide_bonnes_pratiques_secteur) would improve clarity.

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?

With no annotations provided, the description carries full burden and discloses the tool's behavior well: it returns static regulatory information, lists what it covers (who, exemptions, content, etc.), and notes the parameter is merely informational. It does not reveal potential limitations like data freshness, but for an informational tool this is adequate.

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 somewhat lengthy with bilingual repetition, but it is well-structured with clear sections covering different aspects. The front-loaded French summary is efficient, and every sentence adds information. Could be slightly more concise, but it 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?

Given the tool returns static legal information with one optional parameter and no output schema, the description is comprehensive. It covers all key points: who must train, exemptions, content, duration, cost, penalties, and legal basis. No additional information seems necessary.

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 covers the only parameter with full description (100% coverage). The description adds value by stating that the parameter is 'informational' and that the obligation is the same for all types, clarifying that the result does not change based on the parameter. This extra context helps the agent understand the parameter's limited role.

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 mandatory HACCP training rules for French commercial catering. It specifies the resource (obligations légales) and the verb (Retourne), and distinguishes from sibling tools which cover different aspects like corrective actions or checklists.

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 for general information on training obligations but does not explicitly state when to use this tool versus siblings. There is no guidance on alternatives or exclusions, but the context prevents it from being misleading.

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?

No annotations are provided, so the description must disclose behavioral traits. It describes the returned data in detail but does not mention that this is a read-only operation without side effects, authentication needs, or rate limits. While safe to assume, the lack of explicit transparency for a read tool is a moderate 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?

The description is front-loaded with the core purpose and includes both French and English versions, which is helpful. It is readable and contains necessary details, though some repetition exists (e.g., 'the field notes it explicitly' could be removed). Overall, it is efficient given the depth of 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?

Given no output schema, the description thoroughly explains all returned fields (title, editor, year, price, pages, link, key points, regulatory links) and how missing guides are handled. For a single-parameter tool, this is highly complete and leaves no ambiguity about the response.

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 the parameter description already listing allowed values. The main description adds context about sectors and missing guides but does not provide additional semantic meaning beyond the schema. Baseline 3 is appropriate as the description does not degrade but adds little new parameter-specific value.

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 official Good Hygiene Practice Guide reference for a French food-trade sector, listing all details provided (title, editor, year, etc.). The verb 'Retourne la référence' and resource 'GBPH' make the purpose specific and distinguishable from sibling tools focused on HACCP, temperatures, etc.

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 by specifying what it returns and mentions sectors with no distinct validated guide (bakery, cheese, caterer) being flagged. However, it does not explicitly state when to use this tool versus alternatives or provide when-not-to-use conditions. The context of siblings suggests it's for obtaining official references, but exclusions are absent.

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?

With no annotations, the description carries the burden. It describes a read-only lookup with no side effects, but does not explicitly state idempotency or non-destructiveness. It is adequate but not fully explicit.

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 front-loaded with key information and is concise despite being bilingual. No unnecessary sentences, though bilingualism adds length.

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 simple lookup nature and full schema coverage, the description is sufficiently complete. It states the regulatory basis and optional filter, though it does not describe the return structure (no output schema exists).

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 description only adds the optional filter mention. The schema already fully documents the parameter and its values; the description adds no new semantic 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?

The description explicitly states it returns French regulatory food temperatures by product category, citing specific regulations. It distinguishes from sibling tools like get_temperatures_cuisson (cooking temperatures) and get_seuils_microbiologiques, making its unique purpose clear.

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 mentions the optional 'categorie' filter but does not provide explicit guidance on when to use this tool versus siblings. The context is implied but lacks direct when/when-not instructions or alternatives.

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?

No annotations provided, so description carries full burden. It discloses fallback behavior for unrecognized types and describes output details (zones, frequency, product, method, verification). No contradictions.

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?

Well-structured with bilingual content, but somewhat lengthy due to repetition of establishment list. Every sentence adds value.

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 lookup tool with one parameter and no output schema, the description is thorough, covering all aspects of what the tool returns and its compliance context.

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%, already listing valid values and fallback. Description adds no new parameter information beyond what's in 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 explicitly states it returns a model cleaning plan for a French food-establishment type, compliant with GBPH and EU regulation. It lists covered establishment types, distinguishing it from sibling tools focused on HACCP, allergens, etc.

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 indicates the tool is for generating cleaning plans by establishment type, with a fallback to generic 'restaurant' if type not recognized. It provides context but does not explicitly state when not to use or compare with alternatives.

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?

No annotations exist, so description carries full burden. It discloses internal use of another tool and filtering logic, but does not cover latency, error handling, or any side effects. For a non-destructive data retrieval tool, this is adequate but not thorough.

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 concise but has some redundancy (e.g., repeats 'Required 'type_etablissement' at end). It mixes French and English, which may confuse. Structure is logical but could be more streamlined.

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 tool has no output schema, so the description should explain what the output contains. It only mentions returning filtered recalls but omits details on return format, fields, or pagination. This leaves some ambiguity for an AI agent.

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% for the single parameter. The description adds value by providing concrete mapping examples (bakery, fishmonger) and explaining special cases ('restaurant' and 'traiteur' monitor all categories), going beyond the enum list in 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 clearly states the tool returns active RappelConso recalls filtered by establishment type, using specific verbs and resource terms. It distinguishes from sibling tool get_rappels_produits_actifs by noting it internally calls that tool and filters results.

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 when to use this tool (instead of searching all categories) and provides examples per establishment type. It suggests automated daily use. However, it doesn't explicitly state when not to use it or mention alternative tools, though the sibling list implies alternative.

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?

No annotations are provided, so the description carries the full burden. It mentions real-time updates and the official source, but does not disclose read-only nature, authentication requirements, result structure, or pagination 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 bilingual, which adds length but is contextually valuable. It front-loads the purpose and is structured well, though it could be slightly more concise.

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 tool has no output schema, and the description does not describe the fields or structure of the returned recall data, leaving the agent uncertain about what information it will receive.

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 baseline is 3. The tool description adds no additional meaning beyond listing the filters already documented in 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 clearly states that the tool returns active French food product recalls from RappelConso, using specific verbs and resources. However, it does not explicitly distinguish this tool from siblings like 'get_rappels_par_categorie_etablissement'.

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 lists use cases like checking product safety before service and viewing official alerts, but it does not provide guidance on when not to use this tool or mention alternatives among siblings.

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?

No annotations provided. The description details what the tool returns (DLC in days, temperature, source) and covers many categories, but does not disclose any limitations, authorization needs, or data freshness.

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 well-structured with French then English, front-loaded with purpose. It is slightly verbose but each sentence adds value.

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 no output schema and no annotations, the description is fairly complete for a reference tool, covering scope, parameter usage, and examples. Could specify return format details but acceptable.

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% and already describes the parameter well. The description adds examples but does not significantly enhance meaning 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 clearly states the tool returns DLC rules for in-house preparations in French restaurants, listing specific preparation types. It distinguishes from sibling tools which cover HACCP, inspections, scores, etc.

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 clarifies the tool is for DLC rules in French restaurants and mentions an optional filter, but it does not explicitly state when to use it over siblings or 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?

With no annotations provided, the description carries the full burden. It discloses data sources (Alim'confiance, DGCCRF, seasonal patterns), the optional parameter that refines risk, and what the return includes. No contradictions. It could mention limitations like data timeliness or scope.

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 comprehensive but slightly verbose with dual-language paragraphs. It front-loads the purpose and then provides details. Every sentence adds information, but could be tightened to reduce redundancy between French and English.

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 no output schema, the description fully explains the return: risk score, high-risk months, average inspection frequency, and recommendations. For a tool with 3 parameters (2 required) and clear domain, this is complete enough for an agent to use 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 baseline is 3. The description adds value by explaining how `dernier_controle_ddpp` refines the risk score and probability, which is beyond the schema's type/required info. It also lists valid values for `type_etablissement` in the description, partially duplicating 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 clearly states the tool returns an estimated DDPP inspection risk level for a specific establishment type in a French department, using a specific verb 'Retourne' and specifying the resource (risk level). It distinguishes from siblings by focusing on risk estimation rather than other food safety aspects.

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 provides usage context: designed for automation, can be called quarterly. However, it does not explicitly state when not to use it or how it contrasts with sibling tools like `get_score_alimconfiance` or `get_calendrier_obligations`. The recommended call frequency is helpful.

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?

No annotations provided, so description carries full burden. It discloses that the tool returns four sanction levels, thresholds, deadlines, fines, and legal basis. It also notes the optional 'gravite' filter. This is comprehensive for a read-only query tool.

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?

Description is dense with information but includes bilingual repetition (French and English). It front-loads key details, but the structure could be tighter to avoid 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?

For a tool with no output schema, description explains return values (sanction levels, fines, etc.) but does not specify output format (e.g., array of objects, structure). Legal basis is included, but more detail on how the information is organized would improve completeness.

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 one parameter 'gravite' described as optional filter. Description adds meaning by explaining the default behavior (if absent or 'tous', returns all levels) and listing possible values, going beyond the schema's 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?

Description clearly states it returns sanctions and risks for DDPP inspections in French food businesses, listing levels, triggers, fines, and legal basis. It distinguishes from sibling tools focused on other aspects (e.g., HACCP, corrective actions).

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?

Description implies use when sanction details are needed, but lacks explicit guidance on when to use this tool versus alternatives like get_risque_inspection or get_documents_controle_ddpp. No when-not or exclusion criteria.

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?

No annotations are provided, so the description carries full burden. It explains what the tool returns (informational content) but does not explicitly state that it is read-only or has no side effects. However, as an informational tool, the description is mostly adequate.

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 fairly detailed but includes an English translation that repeats information. It is front-loaded with key purpose and usage guidance. Could be slightly more concise, but still effective.

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 no output schema and no parameters, the description fully covers what the tool returns: the 4 score levels, 6 criteria, inspection frequency, and improvement actions. It is complete for an informational 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?

The input schema has zero parameters, so baseline is 4. The description does not need to add parameter info; it correctly focuses on the tool's purpose and output.

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?

Description clearly states the tool returns the complete functioning of Alim'confiance scoring, detailing levels, criteria, inspection frequency, and improvement actions. It explicitly distinguishes from the sibling tool get_alimconfiance_etablissement by noting that the latter retrieves an establishment's specific score.

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 provides explicit guidance: use this tool to understand the scoring system, and for a specific establishment's score, use get_alimconfiance_etablissement. This clearly indicates when to use this tool versus the alternative.

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?

With no annotations provided, the description fully carries the burden of behavioral disclosure. It details what the tool returns, the optional parameter behavior (returns all if absent), and notes a future regulatory change. No contradictions or hidden traits.

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 comprehensive but relatively long due to bilingual content and thorough listing of criteria. It front-loads the main purpose, but could be more concise without losing clarity. Still, every sentence adds value.

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 complexity of the domain and absence of an output schema, the description is remarkably complete: it specifies the regulatory texts, lists all criteria types, sampling plan details, application stages, and even a future change. No gaps apparent.

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 meaningful context: the behavior when 'categorie' is absent or unrecognized (returns all categories). This enriches the schema's enum list with real-world usage semantics.

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 regulatory microbiological criteria for foodstuffs, specifying both safety and hygiene categories and detailed elements like sampling plans. It is distinct from sibling tools which focus on other aspects of HACCP or compliance.

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 implicitly indicates when to use (e.g., when needing microbiological criteria), but lacks explicit guidance on when not to use or comparisons to alternatives among siblings. There is no 'use X instead' 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?

No annotations are provided, so the description carries full burden for behavioral disclosure. It discloses that the tool includes cooling, reheating rules, and safety recommendations for sensitive populations. It also mentions the optional filter, providing clear behavioral context beyond simple retrieval.

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?

Description is front-loaded with the main purpose and includes both French and English versions, which is helpful for bilingual users. It is reasonably concise, though the English translation adds some redundancy. Overall 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?

Given no output schema, the description explains what the tool returns (core cooking temperatures, cooling and reheating rules). However, it does not specify the exact return format or data structure, which would be helpful for agents. Still, for a simple one-parameter tool, it is largely 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?

Schema has 100% description coverage, so baseline is 3. The description adds minimal value beyond the schema, only restating that type_aliment is optional. The schema already explains the filter behavior well.

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 that the tool returns mandatory core cooking temperatures by food type in French catering, providing specific examples (poultry 74°C, minced beef 70°C, etc.). It also distinguishes itself from the sibling tool get_haccp_temperatures, which covers conservation temperatures.

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 that the tool is distinct from conservation temperature tool and names the alternative (get_haccp_temperatures). This provides clear when-to-use and when-not-to-use guidance.

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