Server Quality Checklist

Tool Scores

• compare_listingsB
  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 full burden of behavioral disclosure. It mentions 'normalised' which hints at output formatting, but does not explain behavior on missing listings, invalid IDs, return structure, or failure modes. Significant transparency gap.

  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 no redundant wording. Every word adds value.

  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 simple one-parameter tool without output schema, the description gives the core purpose but lacks details on output format, enrichment meaning, or edge cases. It is minimally viable but leaves notable gaps.

  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% with the 'listings' parameter described as 'Two or more {portal, portalListingId} pairs.' The description adds context about what the comparison covers (price, EPC, etc.) but does not elaborate on parameter syntax beyond the schema, matching the baseline.

  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's function: normalized side-by-side comparison of several listings on specific attributes (price, £/sqft, EPC, enrichment). It is specific about the resource and action, but does not explicitly differentiate from similar sibling tools like find_comparables.

  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 guidance on when to use this tool versus alternatives such as find_comparables or search_listings. The description implies usage for comparing chosen listings, but provides no explicit context or exclusions.

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

• market_statsB
  3.4/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden of disclosing behavioral traits. It does add useful context about data sources (Land Registry + live listings), which hints at reliability and recency. However, it does not disclose limitations such as geographic coverage, update frequency, or whether a session or resolved location is required, leaving some uncertainty.

  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 sentence that front-loads the core purpose ('Area-level market stats') and then lists specific metrics. Every word adds value, with no redundant or filler content. It is appropriately sized for the tool's complexity.

  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 absence of an output schema and annotations, the description provides a solid overview of what the tool returns (a list of metrics) and its data sources. It does not explain how to specify location or property kinds, but those are partially inferable from the schema. For a relatively simple stats tool, it covers most necessary context.

  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 low (33%), and the description provides no additional explanation for location or propertyKinds. It implicitly maps transactionType to metrics (e.g., rental yields to 'rent', prices to 'sale'), but does not explicitly clarify parameter usage. The description does not compensate for the schema's lack of documentation.

  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 identifies the tool as providing area-level market statistics with a specific set of metrics (asking vs achieved prices, £/sqft distribution, rental yields, time on market). This distinguishes it from sibling tools like get_listing and search_listings, which focus on individual listings. However, it lacks an explicit verb like 'get' or 'retrieve', making the action implicit rather than explicit.

  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 for area-level market analysis through its content, suggesting when an agent might need aggregated stats. However, it does not explicitly state when to use this tool over alternatives like search_listings or find_comparables, nor does it mention exclusions or prerequisites. The guidance is only implicit through the listed metrics.

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

• commute_searchA
  3.5/5.0
  Behavior2/5

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

  No annotations are provided, so the description must carry full behavioral disclosure. It only says 'Filter listings... using an isochrone,' without stating whether the operation is read-only, how results are returned, or any edge cases. This leaves significant behavioral ambiguity.

  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, well-structured sentence that front-loads the core action and includes a concrete example. Every word earns its place with no redundancy.

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

  Completeness2/5

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

  Given six parameters, no output schema, and no annotations, the description is too terse. It omits required parameters, does not mention what the tool returns (listings vs. counts), and provides no guidance on how the isochrone is computed or any limitations. This leaves the tool under-specified for an agent.

  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 low (33%), and the description only illustrates destination, maxMinutes, and mode via the example. It does not explain required parameter transactionType or optional filters like maxPrice, minBedrooms, leaving gaps in understanding the full parameter set.

  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 filters listings by travel time to a destination, using a concrete example. It distinguishes itself from siblings like search_listings by focusing specifically on commute/isochrone-based filtering.

  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 clear context on when to use the tool (to filter by travel time) and includes an illustrative query. However, it does not explicitly mention alternatives or exclusionary conditions, so it misses the top score.

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

• find_comparablesA
  3.5/5.0
  Behavior3/5

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

  With no annotations, the description carries the burden. It discloses the data source (Land Registry), recency, proximity, and matching criteria. However, it does not describe output format, edge cases (e.g., no matches), or any side effects/security concerns.

  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 concise sentence that front-loads the key information. Every word contributes to understanding the tool's purpose.

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

  Completeness2/5

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

  With 5 parameters, no annotations, and no output schema, the description is incomplete. It gives a high-level concept but leaves out parameter details, input usage, return structure, and potential limitations.

  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 explain parameters. It only vaguely maps 'recent' to monthsBack and 'nearby' to radiusMiles, but does not define each parameter or the input fields (uprn, address, postcode). It also references property type, size, and bedroom count, which are not input parameters, adding ambiguity.

  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 purpose: retrieving recent nearby Land Registry sales matched on property type, size, and bedroom count. It distinguishes from sibling tools like search_listings or compare_listings by focusing on surveyor comparables.

  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 (for surveyors seeking comparables) but does not explicitly state when to use it vs. alternatives like search_listings or compare_listings. No exclusions or alternative references are provided.

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

• get_listingA
  3.5/5.0
  Behavior3/5

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

  With no annotations, the description must disclose behavioral traits. It mentions 'open-data enrichment,' hinting at external data sources and aggregation, but does not explicitly state read-only, potential latency, or any side effects. The description adds some context beyond a simple 'Get listing' but lacks detail on what the enrichment entails.

  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, focused sentence with key information front-loaded ('Full detail plus full open-data enrichment') and no filler. It is highly concise and well-structured for quick comprehension.

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

  Completeness2/5

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

  Given no output schema and no annotations, the description is too sparse to fully prepare an agent. It does not specify what 'full detail' includes, how enrichment differs from sibling tools, or any potential limitations or prerequisites beyond the parameter identifiers. The scope is so vague that an agent might confuse it with get_property_intelligence or make incorrect assumptions about the response format.

  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?

  The schema already describes 'portal' with an example ('rightmove'), and the description merely repeats the parameter names without adding new meaning. The 'portalListingId' parameter remains undefined in both schema and description. With 50% schema coverage and no compensatory detail, the description adds minimal value beyond the parameter names.

  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 a specific verb+resource: 'Full detail plus full open-data enrichment for one listing' with identification method 'by portal and portal listing id.' This distinguishes it from siblings like search_listings (which likely returns summaries) and get_property_intelligence (which targets property rather than listing).

  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 use when you have a specific portal and portalListingId and need comprehensive data for that listing. However, it offers no explicit guidance on when to choose this over alternatives like search_listings or get_property_intelligence, and there are no stated exclusions or alternative references.

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

• track_searchA
  3.8/5.0
  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 persistence behavior and the delta mechanism (new/reduced since last check). However, it does not explain side effects like storage duration, how to stop tracking, or authentication requirements, providing only partial 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 two short sentences with no redundant information, effectively communicating the core behavior. Every word earns its place.

  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 is adequate for distinguishing the tool and understanding its purpose, but it lacks details on parameters, return values, and state management. For a tool with 5 parameters and no output schema or annotations, the description is not fully complete.

  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 coverage is only 20% (one parameter described). The description adds no parameter-specific semantics, leaving maxPrice, minBedrooms, name, and location undefined beyond their names. This fails to compensate for the low 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 states the tool's function: persist a search and surface new or reduced listings on subsequent calls. This distinguishes it from one-time search tools like search_listings, providing a specific verb and resource.

  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 for tracking searches over time with 'on later calls,' indicating repeated use. It does not explicitly mention alternatives or exclusions, but the context is clear enough for an agent to choose this over a one-time search.

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

• get_property_intelligenceA
  4/5.0
  Behavior3/5

  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 discloses the data scope and the 'open data only' approach, but does not mention potential limitations such as data freshness, coverage gaps, input requirements, or error behavior. This is a moderate level of transparency for a read-only data 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 long, front-loaded with the core purpose, and includes a concise list of data categories. Every word earns its place; it is highly 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?

  Given the tool's moderate complexity and lack of output schema, the description lists the data categories returned, which gives a good sense of the return value. It does not explain the response format or what happens with ambiguous inputs, but it is reasonably complete for a data lookup 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 coverage is 67% (uprn and address have descriptions; postcode does not). The description adds 'address or UPRN' context, suggesting these are alternative identifiers, but it does not clarify the role of postcode or whether any parameter is required. It adds some value but does not fully compensate for the undocumented postcode parameter.

  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 purpose: retrieving 'everything known about an address or UPRN from open data alone.' It lists specific data categories (sold history, EPC, etc.) and distinguishes itself from siblings like get_listing by emphasizing 'no live listing required' and 'zero scraping.'

  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 when to use this tool (when needing open data without live listing requirements) but does not explicitly name alternatives or state when not to use it. The context is clear enough for an agent to differentiate, but lacks explicit exclusions.

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

• search_listingsA
  4/5.0
  Behavior4/5

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

  With no annotations, the description discloses key behaviors: deduplication across portals, enrichment with open data (last-sold price, EPC floor area, etc.), and a coverage flag to prevent silent truncation. This goes beyond the basic purpose and provides significant transparency for an agent.

  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, front-loaded with 'Primary tool' to immediately signal importance. Each sentence adds new information: scope, enrichment, coverage flag. No filler or redundant wording.

  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 tool's complexity (10 parameters, no output schema, no annotations), the description provides a good high-level overview but lacks essential details like pagination limits, how to interpret the coverage flag, and how the enrichment data is returned. It is not fully complete for an agent to invoke it confidently without additional context.

  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 coverage is only 20% (location and transactionType have descriptions), and the tool description does not add meaning for the remaining 8 parameters. It mentions enrichment fields but doesn't connect them to input parameters, so the agent cannot infer how to control result details from the 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 the tool performs a federated live search across all major portals (Rightmove, Zoopla, OnTheMarket), which distinguishes it from sibling tools like resolve_location, get_listing, and market_stats. The verb 'search' and resource 'listings' are specific and 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 calls it the 'Primary tool' for searching listings, implying it should be the default choice. It does not explicitly compare with alternatives like commute_search or market_stats, but the primacy signal provides clear context. However, it lacks explicit exclusion guidelines.

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

• resolve_locationA
  4.3/5.0
  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 describes transformation but does not explicitly disclose that it is read-only or free of side effects. While 'resolve' implies a safe lookup, the lack of explicit safety disclosure leaves a moderate gap.

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

  Conciseness5/5

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

  Two sentences, front-loaded with the action and examples, no wasted words. The pipeline instruction is integrated efficiently.

  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 the simple single-parameter schema and no output schema, the description provides sufficient context: input examples, output types, and downstream usage. It fully equips the agent for this tool's role.

  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%, and the parameter 'query' is adequately described. The description adds examples of valid input formats, but these are illustrative rather than essential for understanding the parameter. Baseline 3 is appropriate.

  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 ('Turn') and defines the exact resource ('free text') and output ('structured geography') with examples. It clearly distinguishes itself from siblings like search_listings by framing itself as the prerequisite resolver.

  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 'Call this first; feed its result into search_listings', giving a clear pipeline and usage context. This is unambiguous and helpful for an agent deciding when to invoke the tool.

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

• list_sourcesA
  4.5/5.0
  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 behavioral specifics: it reports on adapter status, cache age, and coverage completeness. It does not mention side effects (likely none) or behavior with no prior search, but the provided detail is substantive and accurate.

  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: the first defines the tool's output thoroughly, the second gives usage guidance. No wasted words, and the most critical information is front-loaded.

  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 enumerates the key elements returned: which adapters ran, status, cache age, and coverage type. For a zero-parameter, read-only tool, this provides sufficient context for an agent to understand and use the output.

  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 is empty, so there are no parameters to document. The baseline for zero parameters is 4. The description does not need to add parameter semantics since none exist.

  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 begins with 'Provenance for the last search' which clearly identifies the tool's purpose and resource. It then enumerates specific details (portal adapters, status, cache age, coverage) that distinguish it from sibling tools focused on search results. This is a specific verb+resource with clear scope.

  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 states when to use the tool: 'Use this to trust or caveat results.' This provides clear context for applying the tool after a search. It does not explicitly name alternatives or exclusions, but the usage instruction is direct.

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