Server Quality Checklist

Tool Scores

• get_gin_scoreB
  3.1/5.0
  Behavior3/5

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

  With no annotations, the description carries the burden of behavioral disclosure. It usefully details the output components (Quality, Deal, fused verdict), but it does not mention whether the operation is read-only, potential errors, or permissions required. It adds value in explaining the output structure but falls short of full transparency.

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

  Conciseness3/5

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

  The description is a single, somewhat convoluted sentence with jargon and a placeholder (`{GIN}`, `compute_marocain_score`). It is not excessively long, but the structure could be clearer and more direct, detracting from its effectiveness.

  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?

  Given the lack of an output schema, the description outlines the key return components, which is helpful. However, it omits details about the response format, value ranges, or error behavior. The tool's simplicity (one parameter) means the moderate completeness level is acceptable but not exemplary.

  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 schema already provides 100% coverage for the single parameter `id`, describing it as a UUID listing ID. The description adds no additional meaning about the parameter, so the baseline of 3 applies since no compensation is needed.

  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 that the tool provides a coherent GIN verdict for a listing, enumerating the Quality pillar, Deal pillar, and fused buy/hold/pass verdict. This makes the tool's function clear, though it lacks a direct verb and does not explicitly differentiate from sibling tools like `gin_ask` or `get_listing`.

  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?

  There is no explicit guidance on when to use this tool compared to alternatives. The description only implies it is for obtaining a verdict, without any 'use this when' or 'instead of' direction, leaving the agent to infer the appropriate context.

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

• listing_deriveB
  3.1/5.0
  Behavior2/5

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

  With no annotations, the description must carry the burden of behavioral disclosure. It states the output is an AI-derived narrative, implying a generative, likely read-only operation, but it does not disclose whether the tool mutates data, requires special permissions, or has any 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.

  Conciseness5/5

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

  The description is a single, information-dense sentence that front-loads the core purpose. Every element contributes to understanding the tool's function and output, with no redundant or filler content.

  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?

  The description explains the output shape (one-paragraph thesis memo) and the key inputs, which is adequate for a simple tool. However, the lack of usage guidance and potential overlap with gin_deal_memo leaves the context incomplete for an agent to confidently select this tool.

  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 100%, so the schema sufficiently documents the lang and listing_id parameters. The description adds context about what the tool does with the listing (synthesizing a narrative) but does not add specific format or usage details beyond the schema.

  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 tool generates an AI-derived investor narrative for a listing, specifying it as a one-paragraph thesis synthesizing GIN pillars, financial vision, and location. It is distinct from data retrieval tools like get_listing or get_gin_score, though it could be confused with the sibling gin_deal_memo without explicit differentiation.

  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?

  No guidance is provided about when to use this tool versus alternatives. Sibling names such as gin_deal_memo and gin_ask suggest overlapping purposes, but the description offers no selection criteria, prerequisites, or exclusions.

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

• get_marketA
  3.8/5.0
  Behavior3/5

  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 discloses the type of data returned and the geographic scope, but does not mention data freshness, error cases, or read-only semantics. It adds useful context but lacks full behavioral transparency.

  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, information-dense phrase that front-loads the tool's purpose and key data points. Every word contributes value, with no filler or redundant information.

  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?

  Given the tool's simplicity (one parameter, no annotations, no output schema), the description provides sufficient context by listing the data content and the benchmarking context. It does not include return format or error handling, but for a straightforward market-facts tool, this is adequately complete.

  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 input schema has 100% coverage of the single parameter 'scope', including an example. The description adds the 'macro' context but does not provide additional parameter-level syntax or format details. Baseline 3 is appropriate given the high schema coverage.

  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 clearly specifies the tool's function: providing macro market facts for a city or national scope. It lists concrete data points (median price, supply, momentum, catalysts) and mentions the GIN Deal pillar, distinguishing it from sibling tools like search_listings or get_gin_score.

  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 macro market data is needed and mentions benchmarking for the GIN Deal pillar, but it does not explicitly state when to use this tool versus alternatives or provide any exclusions. No alternative tools are referenced.

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

• get_listingA
  4.2/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the behavioral disclosure burden. It explicitly states what is returned and, notably, what is never returned ('Never returns the agent's phone'). It doesn't mention error cases or side effects, but as a read-oriented tool the listing of contents and the negative guarantee add meaningful transparency beyond a generic 'get' description.

  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 sentence that packs a concrete list of return fields and an exclusion. Every clause adds value—no filler or repetition. It is front-loaded with the core purpose and then gives specifics efficiently.

  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 one parameter and no output schema, the description provides a thorough inventory of the response contents, which is the main contextual missing piece. It does not discuss error behavior or authentication, but that is a minor gap for this simple retrieval tool. Overall it gives the agent enough context to invoke it correctly.

  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 schema already describes the only parameter (id as Listing UUID) with 100% coverage. The description does not add semantic detail beyond the schema, so the baseline of 3 applies. It does implicitly confirm that the id refers to a listing, but that is already in the schema.

  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 clearly states that the tool retrieves full detail for a single listing by id and enumerates the specific fields returned (price, AI scores, M-Value AVM, FCR/title trust, provenance, GIN pillars + verdict). It distinguishes from sibling search_listings by focusing on one listing by id, and from get_gin_score by including GIN pillars as part of a full detail set.

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

  Usage Guidelines4/5

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

  The phrase 'Full detail for one listing by id' makes it clear this is for getting a single listing's comprehensive record, implying use when you have a specific id rather than searching. It doesn't explicitly mention when not to use it or name alternatives, but the context is unambiguous enough for the agent to select it appropriately.

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

• search_listingsA
  4.2/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It proactively states that results include {GIN} scores and that agent contact details are never returned, which is a meaningful privacy constraint beyond the schema. It does not disclose pagination/sorting behavior, but the core safety and output traits are covered.

  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 composed of two terse, information-dense sentences. The first immediately names the tool's action and scope; the second delivers the return format and a key constraint. No filler or redundancy exists, and the most important action verb is front-loaded.

  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?

  Given the tool's complexity (7 optional parameters, no output schema, no annotations), the description adequately orients an agent: it defines the domain, the searchable fields, and the return payload (prices and GIN scores). It falls short of explaining how limit and pagination behave, and does not clarify how results are ranked, which would be useful for an agent choosing between this and semantic_search. Still, for a search tool, it is largely complete.

  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 input schema already provides 100% coverage with descriptive comments for all 7 parameters. The description adds minimal parameter-level value beyond restating the filter dimensions (city, typology, price, rooms) already explicitly listed in the schema. It does not introduce new meaning like default behavior or parameter interdependencies, so the baseline 3 applies.

  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 starts with the verb 'Search' and clearly specifies the resource ('AI-graded Moroccan luxury listings') plus the search dimensions (city, typology, price, rooms, free-text query). This distinguishes it from sibling tools like get_listing (single listing lookup) and get_gin_score (score-specific), making the tool's role unambiguous.

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

  Usage Guidelines4/5

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

  The description conveys clear usage context: it is a listing search tool with structured filters and free-text search. However, it does not explicitly mention when to prefer this over semantic_search or get_listing, nor does it note exclusions (e.g., 'use semantic_search for pure relevance ranking'). The intent is clear enough for an agent to select it for listing discovery.

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

• gin_deal_memoA
  4.3/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the safety and behavior burden. It discloses honesty ('won't soften an overpriced verdict'), the non-appraisal nature, and enumerates return sections. It does not explicitly state read-only or cover error cases, but for a generation tool this is strong disclosure.

  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 front-loaded sentence with a compact list of contents followed by two short caveats. Every sentence earns its place with no filler.

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

  Completeness5/5

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

  Despite having no output schema, the description enumerates the memo sections (GIN verdict, M-Value AVM, yield, strengths/risks, district read, next steps), making the return value clear. For a one-parameter tool, this provides complete operational context.

  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 schema already documents the single listing_id parameter with 100% coverage, so the description adds no additional parameter meaning beyond confirming 'one listing id'. This is the baseline for schema-covered parameters.

  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 opens with a specific verb ('Generate') and resource ('structured investor DEAL MEMO') for one listing id, then enumerates the memo's sections. This clearly distinguishes it from sibling tools like get_listing or get_gin_score, which are raw data retrieval rather than synthesis.

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

  Usage Guidelines4/5

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

  It is clear this tool is for generating an investor-focused memo for a single listing, and the 'Decision support, not a certified appraisal' phrase gives context on appropriate expectations. However, it does not explicitly name alternative tools or state when not to use them, so it falls just short of a 5.

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

• gin_askA
  4.4/5.0
  Behavior4/5

  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 several behavioral traits: it is one-shot, plans, searches the catalogue and guides, scores with GIN pillars, and returns citations. It also states a clear negative behavior (does not return agent contact details). This is solid transparency, though it does not cover potential errors or edge cases.

  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 compact (roughly 40 words) and front-loaded with the core action ('Ask...'). Every sentence contributes: it defines the resource, explains the process, gives usage direction with examples, and states a key limitation. No filler or redundancy.

  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 tool with no annotations or output schema, the description is largely complete. It explains what the tool does, how it works, and what it returns (an answer with citations). The only minor gap is that it does not mention what happens if the question is out of scope or unanswerable, but this is acceptable for a natural-language interface.

  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 input schema only describes 'q' as a natural-language question. The description expands on this by specifying that questions should be open-ended and provides concrete examples, which helps an agent formulate appropriate queries. This adds meaningful semantics beyond the schema's basic description.

  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 clearly states this tool asks a one-shot natural-language question to an investment analyst. It specifies the resource (T{AI]GIN) and the action (ask), and distinguishes itself by focusing on open questions rather than structured lookups. Examples of open questions make the purpose unambiguous.

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

  Usage Guidelines4/5

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

  The description explicitly says 'Use for open questions' and provides two example questions, giving clear context for when to invoke this tool. It also mentions a limitation ('Never returns agent contact details'), but does not explicitly name alternative tools for non-open questions, which leaves a slight gap in guidance.

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

• list_servicesA
  4.4/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It adds valuable context about the temporary unavailability of card checkout for instant products, and states that request-based services remain operational. It also discloses the return structure. This goes beyond what the empty schema provides, though it does not mention rate limits or authorization.

  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 information-dense and front-loaded with the main purpose. The lists of services are detailed but necessary for clarity. The note about payment processor unavailability is important but could be considered an addendum. Overall, it is structured effectively and every sentence serves a purpose, though it is slightly verbose.

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

  Completeness5/5

  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 annotations, the description is remarkably complete. It specifies the tool's purpose, the categories of services, the return value's structure, and a temporary operational caveat. For a zero-parameter list tool, this provides sufficient context for an agent to select and invoke it appropriately.

  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?

  There are zero parameters, so the baseline is 4. The description adds meaning by enumerating the product types and explaining that the returned product_type/variant ids are required for order_service. Since there is no schema to describe parameters, the description is the sole source of semantic information, and it does that well.

  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 uses a specific verb ('List') and resource ('transactable services + EUR prices'), and further clarifies the audience (buyers vs agents) and the exact output (product_type, variant ids, price). It clearly distinguishes this from sibling tools like order_service and request_service by stating that the returned data is what order_service needs.

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

  Usage Guidelines4/5

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

  The description provides context for when to use the tool: it lists the services and prices, and explicitly states that the output is needed for order_service. It also notes that request-based services and buyer enquiries work regardless of payment processor issues, implying a use case for request_service. However, it does not explicitly say 'use this when you need prices' or provide exclusions relative to other list/search tools.

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

• order_serviceA
  4.6/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden. It discloses response types (checkout_url vs order_id), billing behavior (no upfront charge for request-only), required email, and a hard restriction ('NEVER returns agent/seller contact'). Minor gaps: no mention of error cases or side effects like order status tracking.

  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?

  Three sentences, front-loaded with purpose, then behavior, then explicit alternative. Every sentence adds value and there is zero fluff or repetition of schema field names.

  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?

  Covers the two product flows, payment mechanism, required fields, and the distinction from request_service. Slightly incomplete regarding what happens on failed payment or invalid product_type, but for a moderate-complexity tool with no output schema, it gives the agent enough to invoke correctly.

  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 coverage is 100%, so the bar is lower, but the description adds relational meaning: product_type + variant come from list_services, and the message field is specifically for request-only products. It clarifies that buyer_email is a hard requirement and explains how parameters map to the two different order flows.

  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 uses a specific verb+resource: 'Place an order for any platform service' with explicit product_type + variant. It clearly distinguishes from sibling request_service by contrasting 'plain buyer enquiry' vs actual order, and separates instant vs request-only products.

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

  Usage Guidelines5/5

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

  Provides explicit when-to-use: ordering a service, and when-not-to: 'For a plain buyer enquiry to a listing's agent, prefer request_service.' Also explains the two product categories and their different flows, giving the agent clear decision criteria.

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

• request_serviceA
  4.7/5.0
  Behavior5/5

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

  With no annotations, the description fully discloses key behaviors: it never returns the agent's contact, the platform intermediates, and for unclaimed listings it returns a note. It also mentions the return of a confirmation reference, covering what would otherwise be unknown.

  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 compact yet information-dense. Every sentence adds a necessary behavioral or usage detail, and the key points are front-loaded (purpose, uniqueness, contact privacy). No fluff or redundancy.

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

  Completeness5/5

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

  Despite no output schema, the description explains return behavior (confirmation reference vs. note for unclaimed). It covers conditions, required fields, and the platform's role. The tool is not overly complex, and all relevant context is provided.

  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 coverage is 100%, so the baseline is 3. The description adds a little extra (why buyer_name and buyer_email are required, examples for service_interest) but these are already present in the schema descriptions. It does not introduce new parameter semantics beyond the structured data.

  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 opens with a specific verb-resource pair ('Submit a buyer ENQUIRY') and clarifies the multi-purpose nature (viewing, valuation, etc.). It distinguishes itself from siblings by stating it is 'the ONLY conversion path' and that it routes to the verified agent.

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

  Usage Guidelines5/5

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

  Explicitly states when to use: for listings with a claimed, verified agent; and what happens otherwise (returns a clear note instead of routing). It also frames itself as the sole conversion path, clearly implying that other tools are not for this purpose.

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

• semantic_searchA
  4.7/5.0
  Behavior5/5

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

  With no annotations, the description carries the full burden and does so well. It discloses the return format ('Returns ranked items with a similarity score') and a key behavioral limitation ('Never returns agent contact details'). It also defines the search scope across specific authored guides, adding context beyond the schema.

  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 concise and well-structured: first sentence states the purpose and scope, second gives usage guidance with examples, third states return behavior and a limitation. Every sentence serves a distinct purpose with no redundancy.

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

  Completeness5/5

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

  Given there is no output schema, the description adequately explains what the tool returns (ranked items with similarity score). It covers scope, when to use, and exclusions. The description fully equips an agent to decide whether and how to invoke the tool, even for a search tool with a relatively simple interface.

  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 100% with clear descriptions for all three parameters. The description adds example queries that illustrate the 'q' parameter, but it does not provide additional semantic meaning beyond the schema. Baseline 3 is appropriate when the schema already carries the parameter documentation.

  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 clearly states the tool's function: 'Semantic / conceptual vector search across the Moroccan catalogue AND the authored guides'. It uses a specific verb ('search') and explicitly names the resources. It also distinguishes itself from exact-filter search tools by saying it handles queries 'that don't map to exact filters', which differentiates it from siblings like search_listings.

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

  Usage Guidelines5/5

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

  The description explicitly states when to use the tool: 'Use for fuzzy / lifestyle / thesis queries that don't map to exact filters', with concrete examples. It also implicitly defines when not to use (when queries map to exact filters) and notes a limitation ('Never returns agent contact details'), giving clear usage context.

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