Vintage Postcard

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

The annotations already declare readOnlyHint=true, so the description does not need to disclose safety. It adds that the tool returns aggregated 'key figures' rather than raw data, which is a slight behavioral insight, but it does not explain pagination, caching, or error behavior. With annotations covering the main safety profile, the description adds minimal extra value.

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 front-loads the key phrase 'Chiffres clés de la boutique' and lists the exact data points. There is no redundancy or wasted words, making it highly 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 there is no output schema and no parameters, the description adequately covers what the tool returns by enumerating the expected data categories. The list of items (posters count, countries, price range, formats, frame price, delivery rules) is sufficient for an agent to understand the tool's scope. It is complete for a simple overview 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 tool has zero parameters, so the baseline is 4. The description clarifies the purpose of the tool (overview metrics) but does not need to explain parameter semantics since there are none. It adds meaning by specifying what the returned data covers, which is helpful for an agent seeking an overview.

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 key figures of the shop, listing specific data points (number of posters, countries, price range, formats, frame price, delivery rules). This differentiates it from sibling tools like get_store_policies or list_destinations, making its purpose unambiguous.

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 does not provide explicit guidance on when to use this tool versus alternatives. While the name and content imply it is for getting a general overview, there is no mention of when not to use it or mention of alternative tools. The context is implied rather than stated.

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, covering safety. The description adds that the returned status is one of pending, paid, or canceled, providing domain context. It does not mention potential errors or response format, but for a read-only tool with no output schema, the additional status list is moderate value.

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, well-structured sentence that front-loads the purpose and includes the identification methods. No fluff, all informative. It is appropriately 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?

For a simple read operation with 3 parameters, no required fields, and no output schema, the description covers the key aspects: what the tool returns, how to specify the order, and the possible statuses. It doesn't specify precedence when multiple inputs are given or error conditions, but these are minor gaps for a read-only status tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate. It does by mapping parameters to real-world meaning: order_id is the order number, email is the customer email, and session_id is the session identifier. It also clarifies the combination logic (either order_id+email or session_id alone), which is beyond simple schema definitions.

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's purpose: retrieving the status of an order (pending, paid, canceled). It specifies the identification methods (order number + customer email or session ID), which distinguishes it from other getter tools like get_catalog_overview or search_postcards. The verb is implicit but the resource and result scope are unambiguous.

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 clear usage context by explaining the two ways to specify an order (order_id + email or session_id). It implies when to use this tool (when order status is needed), but does not explicitly contrast with sibling tools or mention exclusions. Still, the identification methods serve as practical 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 mark it as read-only and closed-world, so the description does not need to restate safety. It adds useful behavioral context by enumerating what the record includes (price, strikethrough price, formats, frame option, image, shipping costs, similar posters) and that either an ID or city name can be used. It does not describe not-found or ambiguity behavior, but annotation coverage lowers the required burden.

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 concise sentences front-load the core purpose and then provide a compact list of returned fields. Every word contributes meaningful information, with no filler or repetition of annotation content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only lookup with only two parameters, the description is sufficiently complete: it enumerates the returned content and the accepted lookup keys. With no output schema, listing the fields is valuable; only edge-case behavior (e.g., ambiguous city names or missing IDs) is left unspecified.

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 100% description coverage for both parameters, so the baseline is 3. The description mostly restates the schema's anyOf requirement ('accepts an identifier or a city name'), and it even narrows 'ville / lieu' to just 'ville'. It adds no new format, type, or constraint detail beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool returns a complete record for a single poster ('Fiche complète d'une affiche') and lists the specific content fields. This distinguishes it from sibling tools like search_postcards, get_catalog_overview, and list_destinations by signaling a detail-retrieval purpose.

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 phrase 'Accepte un identifiant ou un nom de ville' and the emphasis on a complete record imply this tool is for retrieving one poster's full details, but there is no explicit guidance about when to use it versus alternatives such as search_postcards or get_catalog_overview. No when-not or exclusion criteria 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?

Annotations already declare readOnlyHint=true, so the description doesn't need to restate that. The description adds that the tool provides policy information to cite, which is useful. However, it doesn't disclose any additional behavioral traits (e.g., whether it returns static content, whether it's always up-to-date). With annotations covering the safety profile, 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 extremely concise: one short sentence listing the content areas plus a usage directive. Every word earns its place, and it's front-loaded with the key topics. No waste.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (no parameters, no output schema, read-only), the description is complete enough. It tells the agent what content is covered and that it should be cited. It doesn't explain the return format, but with no output schema and a simple policy lookup, that's acceptable. The description covers the essential 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?

The tool has zero parameters, and schema description coverage is 100% (trivially, since there are no properties). The description adds meaning by listing the content areas (delivery, returns, formats, payment, FAQ), which helps the agent understand what information is available. Since there are no parameters, the description compensates 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 the tool provides store policies (delivery, returns, formats, payment methods, FAQ) and is distinct from siblings like get_catalog_overview or get_order_status. It could be more specific about the resource (store policies) but the verb 'get' and the listed topics make the 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 includes 'À citer plutôt que de deviner' (to cite rather than guess), which implies when to use it: when needing factual policy information instead of assuming. It doesn't explicitly contrast with alternatives, but the context of sibling tools (e.g., get_order_status) makes 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?

Annotations already indicate readOnlyHint=true, so the tool is safe to call. The description adds that the result is grouped by country and includes counts and examples, which is useful output context. No contradiction.

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 sentence, concise, no fluff. It clearly and efficiently communicates the tool's purpose.

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 list tool with no output schema, the description provides enough detail about the output (grouped by country, with counts and examples). It could mention sorting or pagination, but given the simplicity, it's adequately 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?

There are no parameters, so schema coverage is 100%. Baseline is 4, and no extra param info is needed.

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 lists all destinations from the catalog, grouped by country with poster counts and examples. This distinguishes it from siblings like get_catalog_overview, which likely provides a broader overview.

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 does not specify when to use this tool versus alternatives like get_catalog_overview or search_postcards. It lacks explicit guidance on when to prefer 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?

The description goes well beyond the annotations by explaining the actual payment flow: hosted_checkout returns a Stripe link for the client to confirm, while delegated_token confirms immediately. It also discloses important constraints such as API-key authentication and per-order caps. There is no contradiction with the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and front-loaded with the core purpose, followed by two scannable method bullets. Every sentence adds useful information and there is no filler or repetition of 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?

Given the tool's moderate complexity and lack of an output schema, the description provides sufficient context: the prerequisite start_order, the two payment modes, and the restrictions on delegated_token. It enables an agent to decide which method to use and what the expected behavior will be.

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?

Though the schema already documents session_id and payment_token, the description adds meaningful semantics for the method parameter, explaining what each enum value does behaviorally. With 67% schema coverage, this compensation is important and effectively clarifies how the parameters relate to the two payment flows.

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 action ('Déclenche le paiement') tied to a precise resource ('session ouverte avec start_order'), making the tool's purpose immediately clear. It also distinguishes the two payment methods and differentiates itself from sibling tools like start_order and quote_cart.

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 clearly states when to use the tool: after start_order has opened a session. It also provides method-specific context for hosted_checkout versus delegated_token, including the reservation of delegated_token for API-key-authenticated agents. It doesn't explicitly list excluded cases, but the context is strong enough for selection.

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 indicate readOnlyHint: true, so the description does not need to reiterate safety. It adds value by listing the quote components (subtotal, frame, shipping, total), giving the agent insight into what the tool returns. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence that conveys purpose and usage without fluff. Every word 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?

There is no output schema, so the description appropriately describes the output (subtotal, frame, shipping, total). It does not delve into input structure, but given the schema defines items clearly and the tool is a simple quote calculator, the description is nearly complete. It could mention the free-shipping threshold more explicitly, but it is already implied.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description does not explain how to construct the 'items' parameter (e.g., product_id required, size enums, quantity limits, with_frame). It only hints at 'option cadre' but misses quantity and size. The schema itself is detailed, but the description should compensate for the low coverage, which it does not.

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 computes an exact cart quote with subtotal, frame option, shipping (free over 30€), and total. It also specifies the usage context: before announcing a price to the customer. This distinguishes it from sibling tools like start_order or pay_order, which involve order lifecycle steps.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description gives explicit timing guidance ('À utiliser avant d'annoncer un prix au client') but does not mention alternative tools or exclusions (e.g., 'use start_order to actually place an order'). It is clear enough for basic usage.

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

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

The annotations declare readOnlyHint=false, consistent with a write operation. The description adds meaningful context: it is a request submission, not a direct creation, and the team will recontact the client via email, implying asynchronous processing. This goes beyond what annotations specify, enhancing transparency about expected 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 two sentences, front-loaded with the primary purpose, and includes the key fields and expected follow-up. Every sentence adds value with zero redundancy. 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 simple request tool with no output schema, the description covers the main action, key inputs, and the post-submission process (email contact). It does not detail response formats, but that is not essential here. Given the tool's simplicity and the annotations, it is reasonably 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 schema already describes city, style, and additional_info with 75% coverage. The description mentions these fields, but adds little beyond what is in the schema. Email is required but lacks a schema description, and the description does not clarify it either. Given high coverage, baseline 3 is appropriate; no additional syntax or meaning is provided.

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's purpose: 'Enregistre une demande de création d'affiche vintage sur mesure' (Records a request for a custom vintage poster). It specifies the action (record), resource (custom poster request), and key fields (city, style, details). This distinguishes it from sibling tools like start_order or get_postcard.

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 does not explicitly state when to use this tool versus alternatives. It implies use for custom poster requests but lacks any mention of when not to use or alternative tools (e.g., for standard orders use start_order). The only context is the workflow description (team recontacts client), which is more behavioral than 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?

Les annotations déjà fournies indiquent readOnlyHint=true et openWorldHint=false. La description ajoute la portée du catalogue et les champs retournés (prix, promo, image, URL), ce qui donne un contexte utile mais manque de détails sur le comportement de pagination, le tri ou l'effet des paramètres non documentés.

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?

Deux phrases courtes qui vont à à l'essentiel : la première annonce l'action et les filtres, la seconde précise les champs retournés. Pas de remplissage, pas de répétition du titre.

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?

Aucun schéma de sortie n'est donné, donc la mention explicite des champs retournés (prix, promo, image, URL) est importante. La description est suffisante pour comprendre l'objectif du ouil, mais elle n'indique pas ce qui se passe avec le pagination (limit/offset) ou le tri si on les utilise ; ces éléments ne sont visibles que dans le schéma.

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?

La couverture du schéma est de 67% : query, région, pays, min_price, max_price et collection ont déjà une description, que la description reprend globalement. Pour sort, limit et offset, il n'y a aucun éclaircissement supplémentaire. La description compense un peu, mais pas complètement pour ces paramètres restants.

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 l'action : « Recherche dans tout le catalogue d'affiches anciennes » et énumère les dimensions de filtrage (mot-clé, collection, prix). Elle n'indique pas explicitement les frères comme get_postcard ou list_destinations, mais le rôle de recherche est sans ambiguïté.

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?

Le contexte d'utilisation est implicite : ce descripton est pour la recherche de l'ensemble du catalogue avec des filtres, mais il n'indique pas quand l'utiliser par rapport aux autres outils frères, ni quel outil utiliser pour obtenir un objet spécifique. Aucune alternative ou exclusion n'est explicitée.

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 only indicate non-read-only, non-destructive, non-idempotent. The description adds critical context: this creates a sessionhol and returns an ID for later payment, explicitly stating no payment is triggered. It doesn't discuss side effects like persistence or validity, but it clearly sets expectations for a creation operation.

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?

Single, dense sentence that front-loads the core purpose ('crée une session de commande'), then gives the return value and the next-step reference. No wasted words, no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description explains the session creation, returns its ID, and explicitly notes no payment is triggered, positioning it correctly relative to pay_order. It references the cart, email, and shipping, and mentions the ID for later use. It's a solid match for the tool's role in an order flow, though it doesn't cover edge cases like validation or persistence.

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 description names the key inputs (panier, email, adresse de livraison optionnelle) which maps to items, email, and shipping_address. However, it doesn't elaborate on first_name/last_name or the meaning of each item field, and the schema itself already provides property descriptions. The description adds the important context that the return value is an ID to use with pay_order, but does not deeply explain parameter usage 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 creates an order session (panier + email + optional shipping address) and returns an identifier for later use with `pay_order`. This is a specific verb+resource with clear scope, distinguishing it from payment or status tools.

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 says the returned identifier is to be used with `pay_order`, which establishes the correct sequence and implies when to use this tool. It also clarifies that no payment is triggered, which helps avoid misuse. However, it doesn't mention alternatives or exclusions, so not a perfect 5.

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