Server Quality Checklist

Tool Scores

• preview_remove_from_cartB
  3.2/5.0
  Behavior3/5

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

  The description adds useful behavioral context: it creates a 'confirmation à usage unique' (single-use confirmation) and explicitly states 'Ne modifie pas le panier' (does not modify the cart), clarifying the non-destructive nature. However, the annotations already set destructiveHint=false and idempotentHint=false. The description adds the single-use confirmation detail which is genuinely valuable, but doesn't explain what happens to the confirmation if unused or its relationship to confirm_remove_from_cart.

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

  Conciseness4/5

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

  Two sentences, highly efficient. The first sentence covers purpose and behavior, the second clarifies non-destructive nature. No wasted words. Could arguably add a third sentence on when to use, but as written it's tight and well-structured.

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

  Completeness3/5

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

  For a single-parameter preview tool with no output schema, the description explains the core function well. It's relatively simple functionally (preview create confirmation). However, it could better explain the confirmation lifecycle (does it expire? what does calling preview_remove_from_cart then confirm_remove_from_cart look like?) and would benefit from explaining what 're-lire le panier' behavior implies visually for the agent. The missing output schema means the agent doesn't know what this returns, and the description doesn't compensate.

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

  Parameters3/5

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

  The single parameter 'reference' has 0% schema description coverage, so the description carries the burden. It mentions 'la ligne ciblée' (the targeted line) which maps to reference, implying reference identifies a cart line. However, it doesn't clarify whether reference is a product ID, line ID, or what format beyond the schema's alphanumeric pattern. This is an implication rather than explicit explanation.

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

  Purpose4/5

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

  The description states a specific action: 'Relit le panier et crée une confirmation à usage unique pour retirer toute la ligne ciblée' (re-reads the cart and creates a single-use confirmation to remove the targeted line). It has a clear verb+resource (relit/preview remove) and explicitly notes it does not modify the cart, distinguishing it from confirm_remove_from_cart sibling.

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

  Usage Guidelines2/5

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

  While the description implies this is a preview that should be followed by confirm_remove_from_cart (given the mention of a single-use confirmation and the sibling confirm_remove_from_cart tool), it does not explicitly say 'use this before confirm_remove_from_cart' or explain the relationship with the confirm tool. No exclusion criteria or alternatives named.

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

• confirm_remove_from_cartB
  3.4/5.0
  Behavior3/5

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

  Annotations already declare destructiveHint=true and readOnlyHint=false, covering the destructive nature. The description adds valuable context beyond annotations: it rejects modified carts (optimistic concurrency), verifies the real cart afterward, and requires a confirmationToken. However, it doesn't disclose what happens on rejection (error behavior, partial execution) or authentication requirements. The description is consistent with the destructiveHint annotation, adding meaningful behavioral context without contradicting structured data.

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

  Conciseness4/5

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

  One dense sentence covering the full lifecycle: consume, reject-if-changed, remove, verify. No wasted words. While complete, the French structure packs many subordinate clauses; a reader might benefit from slightly clearer segmentation, but this is efficient for the information conveyed.

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

  Completeness3/5

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

  For a mutation tool with destructiveHint=true, no output schema, and 0% param schema coverage, the description carries a heavy burden. It does explain the transactional behavior (reject if modified) and post-action verification, which is good. However, it lacks error/return information, what happens on confirmation token expiry, and whether the tool can fail silently. Given the tool's moderate complexity (1 param, clear state-machine behavior), the missing return-value documentation is a notable gap.

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

  Parameters3/5

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

  The description mentions the confirmationToken concept ('Consomme une confirmation') and 'refuse tout panier modifié' relates to its validation behavior. However, with 0% schema description coverage and an opaque 43-character token pattern, the description doesn't explain where the token comes from (presumably from preview_remove_from_cart). It adds partial meaning but leaves the token's origin and format details unexplained.

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

  Purpose4/5

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

  The description clearly states the verb (confirm/consume) and resource (retrait d'une ligne du panier). It explains the multi-step behavior: consumes a confirmation, rejects modified carts, removes the line, verifies the real cart. It doesn't explicitly distinguish from sibling tools, but the 'confirmation' aspect sets it apart from preview_remove_from_cart, though this differentiation is only implicit.

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

  Usage Guidelines3/5

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

  The description implies this is the confirmation step following preview_remove_from_cart (sibling tool), indicating a two-phase pattern. However, it doesn't explicitly state when to use this versus alternatives or describe the required prerequisites like obtaining a confirmation token first. The 'refuse tout panier modifié entre-temps' gives context on a behavioral constraint but not explicit usage direction.

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

• get_productB
  3.4/5.0
  Behavior4/5

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

  Annotations already provide readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is fully disclosed. The description adds the note that food information is included in the read, which is behavioral context beyond annotations. With strong annotation coverage, the description's additional context is meaningful but not extensive.

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

  Conciseness4/5

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

  The description is a single clean sentence with no waste. It covers the core purpose and scope efficiently. It could add a small amount of parameter guidance but is otherwise appropriately concise.

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

  Completeness3/5

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

  For a read operation with strong annotations (readOnly, openWorld, no output schema), the description captures the essential purpose. However, with 0% schema coverage, both parameters remain semantically under-explained, and there is no mention of what the returned product data looks like. For a fairly simple 2-param read tool, this is adequate but not thorough.

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

  Parameters2/5

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

  Schema description coverage is 0%, so the description must compensate for the two parameters (reference and slug). The description only mentions these fields by name without explaining their format or semantics (e.g., that reference is an alphanumeric product ID and slug is a URL-friendly identifier). It does add that both are used to locate the product but provides no guidance on how to obtain or format them.

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

  Purpose4/5

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

  The description uses a specific verb ('Lit') with a clear resource ('fiche produit publique') identified by its two key fields (référence et slug). It also notes the inclusion of food information, adding useful scope. It does not explicitly distinguish it from siblings like search_products, but the read-by-reference/slug purpose is clear enough to differentiate.

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

  Usage Guidelines3/5

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

  The description implies this is for reading a single public product by exact reference and slug, which suggests it is for fetching a known product rather than searching. However, it does not explicitly state when to use this versus search_products, nor mention prerequisites (e.g., whether the product must already exist, or whether 'public' means no auth needed). The when-to-use is implied but not articulated.

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

• search_productsA
  3.5/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=true, and idempotentHint=true, which covers the safety and repeatability profile well. The description adds the 'publique' (no-auth needed) context, which is valuable. No contradictions detected. However, it doesn't disclose return format, pagination count, price observation context, or any rate limits. With strong annotations, a 3 is appropriate as the description adds modest value beyond them.

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

  Conciseness5/5

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

  A single compact sentence in French that efficiently conveys purpose, scope, and output. Zero wasted words. Extremely concise and appropriately sized for a simple list-search tool.

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

  Completeness3/5

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

  This is a relatively simple 2-parameter, read-only, idempotent search tool with strong annotations. The description adequately conveys the core function. However, given it's an e-commerce catalog search (Greenweez), details like language/locale assumptions, whether results are sorted, or what 'prix observés' means could add value. But for a simple search tool with good annotations, this is near-complete. Not a 5 because some behavioral detail (e.g., result count, sorting, relevance) is omitted.

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

  Parameters3/5

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

  Schema description coverage is 0%, so the description carries the burden for parameter meaning. However, the description mentions 'page de produits' which implies the page parameter controls pagination, and 'query' is self-explanatory as the search term. For only 2 simple parameters, this marginal coverage is adequate. The description adds some meaning inferable beyond schema, but doesn't explicitly document either parameter.

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

  Purpose4/5

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

  The description clearly states the verb (recherche/searches), resource (catalogue Greenweez), and the output (une page de produits avec les prix observés). This is a specific public catalog search. However, it doesn't explicitly distinguish itself from siblings like get_product, though 'recherche publique' + pagination ('une page de produits') helps differentiate the list/search scope from a single-product fetch.

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

  Usage Guidelines3/5

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

  The description implies usage context ('Recherche publique dans le catalogue') but provides no explicit when-to-use guidance or alternatives. It doesn't state when to use this vs get_product or against the cart operations. The 'publique' qualifier hints it's a no-auth search, which is useful, but no exclusion or comparison to sibling tools is given.

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

• connect_greenweezA
  3.6/5.0
  Behavior3/5

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

  Annotations provide idempotentHint=true and openWorldHint=true, and the description adds the useful detail that credentials remain on Greenweez (data stays on the destination), which is a meaningful addition. However, it doesn't disclose more about the wizard behavior or potential side effects beyond what annotations cover.

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

  Conciseness4/5

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

  Description is a single concise sentence plus a security-relevant note. It's efficient and front-loaded with the main purpose. The second sentence adds the credential-handling detail which is valuable context, not waste.

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

  Completeness4/5

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

  For a zero-parameter tool that opens a local wizard, the description covers purpose, scope, and the security property of credentials. It's complete for the simple nature of this tool, though it could mention what user action is expected after the wizard opens.

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

  Parameters4/5

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

  The tool has 0 parameters with 100% schema coverage, so per rubric the baseline is 4. There is nothing for the description to add about parameters since none exist; the description correctly explains the tool needs no inputs and returns a wizard.

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

  Purpose4/5

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

  Description clearly states it returns a wizard with two links for login or account creation, with a specific verb+resource. It differentiates the connection/auth purpose from the sibling shopping-cart tools. However, it doesn't explicitly contrast with siblings beyond the implicit scope difference.

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

  Usage Guidelines3/5

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

  The description implies usage (when a user wants to connect or create a Greenweez account) but provides no exclusions or comparison to alternatives. It doesn't state when NOT to use this tool or point to other tools for related flows.

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

• preview_add_to_cartA
  3.8/5.0
  Behavior4/5

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

  Annotations declare readOnlyHint=false (a mutation may occur), but the description explicitly states 'Ne modifie pas le panier', which adds useful nuance clarifying the tool creates a confirmation artifact without altering the cart. It also discloses the single-use and two-minute validity behaviors, adding real context beyond annotations. 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.

  Conciseness5/5

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

  Two sentences, front-loaded with the read action then the creation behavior, followed by a clarifying non-mutation clause. Zero wasted words; every clause earns its place.

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

  Completeness4/5

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

  For a tool with 2 params, good annotations, and no output schema, the description covers the key behaviors: what it reads, what it creates (single-use confirmation, 2-minute validity), and what it does NOT do (doesn't modify the cart). The main gap is not describing the return value/response format, but with no output schema and a clear confirmation concept, the completeness is adequate.

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

  Parameters3/5

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

  Schema description coverage is 0%, so the description carries no parameter explanation. However, reference and slug both have clear patterns in the schema (alphanumeric slug-like identifiers), and these are standard identifiers already well-documented by the pattern constraints. The description doesn't add param meaning but the schema's regex patterns carry reasonable semantic weight despite 0% coverage.

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

  Purpose4/5

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

  Description clearly states it reads the sheet/offer/stock/cart and creates a single-use confirmation valid for two minutes. The verb (relit/crée), resource (panier context), and behavior (preview confirmation) are specific. It doesn't explicitly distinguish from sibling preview_remove_from_cart or confirm_add_to_cart, but the 'ajout au panier' vs sibling names make the distinction reasonably clear from context.

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

  Usage Guidelines3/5

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

  The description implies a preview (non-mutating) flow before add-to-cart, and the 'Ne modifie pas le panier' clause clarifies it's a safe pre-step. However, it doesn't explicitly state when to use this vs confirm_add_to_cart or preview_remove_from_cart, nor the alternative flows. Usage context is implied rather than spelled out.

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

• get_cartA
  3.9/5.0
  Behavior4/5

  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 agent knows this is a safe read operation. The description adds context beyond annotations by noting it reads the cart of the connected account and excludes sensitive data, which is genuinely useful for agents deciding whether this action touches protected resources. No contradictions 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.

  Conciseness5/5

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

  A single, tight French sentence that conveys the purpose and scope exclusions. Zero wasted words, no redundancy with the schema or annotations. Efficient and well-structured.

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

  Completeness4/5

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

  For a simple no-parameter read tool with strong annotations (readOnly, idempotent, non-destructive), the description covers the essential purpose and scope. It doesn't describe the return format or pagination, but with no output schema and simple semantics, this is less critical. It's complete enough for an agent to safely select and invoke.

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

  Parameters4/5

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

  The tool has 0 parameters and schema coverage is 100%, so there is nothing to document. The baseline for 0 params is 4, and the description appropriately does not invent any parameter details. Nothing more is needed here.

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

  Purpose4/5

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

  The description states a clear verb+resource: it 'relit' (re-reads) the real cart of the connected account. It adds useful scope clarification by explicitly stating it does NOT ask for addresses, payments, or profile data, which distinguishes it from broader account-reading tools. However, it doesn't explicitly distinguish from the cart sibling tools (preview_remove_from_cart, etc.) which are about modification rather than reading.

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

  Usage Guidelines3/5

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

  The description clarifies what data is excluded (addresses, payments, profile) but doesn't explicitly state when to use this vs alternatives. Among siblings, the closest ambiguity is with get_product/search_products (catalog reads), but that distinction is implied by context rather than stated. No explicit when-not guidance or alternative naming.

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

• confirm_add_to_cartA
  4.2/5.0
  Behavior4/5

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

  Beyond annotations, the description discloses significant behavioral traits: the tool refuses a modified cart, adds exactly one unit, and verifies the actual cart after. With readOnlyHint=false and openWorldHint=true already signaling mutation and side effects, the description adds meaningful detail about concurrency guards (refusing modified carts) and quantity semantics (exactly one unit).

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

  Conciseness5/5

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

  The description is a single compact French sentence that conveys purpose, usage constraints, quantity semantics, and a verification step. Every clause earns its place with zero filler.

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

  Completeness4/5

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

  For a single-parameter confirmation tool with no output schema, the description covers the core behavior efficiently. It could add details on error outcomes (e.g., what happens when a cart is modified or token is invalid), but given the tool's simple structure and the openWorldHint annotation, the coverage is reasonably complete.

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

  Parameters4/5

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

  Schema description coverage is 0%, so the description must compensate, and it partially does: the confirmationToken is implicitly a token obtained from a prior preview step, tying it to the add-to-cart confirmation workflow. However, it doesn't specify the token's format beyond the schema pattern, or what happens with an invalid/expired token, though with only one parameter the description carries reasonable weight.

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

  Purpose5/5

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

  The description states a specific verb (consume/confirm) plus resource (addition to cart), and details what it does: consumes a confirmation, refuses modified carts, adds exactly one unit, then verifies the actual cart. This distinguishes it from siblings like confirm_remove_from_cart and preview_add_to_cart.

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

  Usage Guidelines3/5

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

  The description implies this is the confirmation step following preview_add_to_cart, and its refusal behavior hints at when it should be used. However, it doesn't explicitly name the alternative (preview_add_to_cart) or state when NOT to use it, leaving the workflow linkage implied rather than explicit.

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