Server Quality Checklist

Tool Scores

• get_listingA
  4/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden. It discloses the output contents (complete description, photos, floorplans, agency/agent contacts) and accepts input formats. However, it omits any discussion of error handling, rate limits, or what happens when a listing is unavailable or invalid, which are notable gaps for an unannotated tool.

  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 two sentences, front-loaded with the primary action 'Fetch full detail' and immediately specifying the resource. It avoids fluff, making every word count while remaining concise 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 one-parameter fetch tool, the description adequately explains the input format and the key output components (photos, floorplans, contacts). However, it lacks details about potential error conditions or whether the listing must be currently active, which would round out the 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 provides a full description of the sole parameter (listing) with examples of URL and numeric ID, achieving 100% coverage. The tool description repeats the same information without adding new meaning, so it does not enhance the schema beyond what is already documented.

  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 fetches full detail for one realestate.com.au listing, enumerating specific content like photos, floorplans, and contacts. This distinguishes it from sibling tools such as search_listings, which likely return multiple listings, by focusing on a single record.

  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 implies usage when you have a specific listing URL or numeric ID, providing clear context for when to use this tool. However, it does not explicitly name alternatives or state when not to use it, though the single-listing focus inherently guides appropriate selection.

  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 transparency burden. It discloses pagination limits ('up to 25 listings per page') and the return fields (address, price, bed/bath/car counts, land size, agency, agents, inspection times, auction dates), which is valuable context. It does not mention rate limits, error behaviors, or whether results are sorted, but for a search tool this is adequate.

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

  Conciseness5/5

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

  The description is three sentences: the first states the main purpose, the second details the return value, and the third gives a usage prerequisite. Every sentence adds meaningful information without redundancy or 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?

  Given the tool's complexity (11 parameters, no output schema, no annotations), the description covers the most critical aspects: what it returns, pagination behavior, and a key prerequisite. However, it does not mention channel-specific parameter relevance (e.g., minLandSize for rentals) or the default channel, leaving some ambiguity for agents constructing sophisticated queries.

  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 45%, so the description must compensate. It adds context about the result fields and pagination, which helps infer how parameters like maxPrice and minBedrooms affect results. However, it does not explain the semantics of several parameters with no schema description (e.g., excludeUnderContract, propertyTypes), though their names are self-explanatory. Overall, it partially compensates but not fully.

  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 searches realestate.com.au for properties to buy, rent, or recently sold. The verb 'search' with the specific resource and the channel options (buy/rent/sold) make its purpose unambiguous and distinguish it from sibling tools like get_listing and resolve_location.

  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 explicitly instructs the agent to call resolve_location first when the user's location is vague or misspelled, which is a clear directive for when to use an alternative. However, it does not mention when to use get_listing (e.g., for retrieving details of a single listing), leaving that distinction implied by the name rather than explained.

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

• resolve_locationA
  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 performance ('Fast, no browser needed') and the behavior of returning multiple canonical names for ambiguous input. It doesn't cover edge cases like no-match, but the core behavior is well disclosed for a simple resolver.

  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 primary purpose, followed by a usage suggestion and example. Every sentence adds value, and the structure is highly readable and efficient.

  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?

  The description fully explains what the tool does and how to use it relative to siblings. It doesn't include the exact return format or error behavior, but for a simple resolver, the information given is sufficient. The example adds context for ambiguity handling.

  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 provides a description for 'query' but not for 'max'. The tool description adds meaning by explaining query as partial/ambiguous location text and showing an example with multiple results, which implies max controls the result count. However, max's semantics are not explicitly explained, and with only 50% schema coverage, the description only partially compensates.

  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: turning partial/ambiguous location text into canonical REA suburb/region names with state and postcode. It uses a specific verb+resource and differentiates itself from the sibling search_listings and get_listing tools.

  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 tells when to use the tool ('before search_listings') and provides a concrete example ('bondi' returns multiple suburbs). It also mentions it's fast, giving a reason to prefer it for disambiguation, and names an alternative, making 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.