Server Quality Checklist

Tool Scores

• about_microfarmA
  3.5/5.0
  Behavior4/5

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

  With no annotations provided, the description must carry the full burden of behavioral disclosure. It accurately conveys that this is a read-only, non-destructive information tool with no stated side effects. The description honestly represents the tool's output as an explanation. However, it could be more explicit that this likely returns static textual content and doesn't query external data.

  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, well-structured sentence that front-loads the core purpose ('plain-language explanation') and immediately specifies the two topical areas. No wasted words; every element contributes to the definition. It is concise without being under-specified.

  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 simple informational nature of the tool, the description is nearly complete for an agent to understand its purpose and content. While it could benefit from mentioning the expected format of the response (e.g., 'returns a paragraph'), the description covers the essential 'what' and 'why' sufficiently. The main gap is the undocumented parameter, which is already penalized in the parameter semantics dimension.

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

  Parameters1/5

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

  The schema defines a single required 'text' parameter with zero description coverage. The tool description provides absolutely no guidance on what this parameter means, what format it should be in, or how it should be populated. For a required parameter, this is a critical gap that forces the agent to guess.

  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 this tool provides a 'plain-language explanation' of micro-farms and what to look for in land. This distinguishes it from the action-oriented sibling tools (find_land, assess_land) by being informational rather than transactional, though it doesn't explicitly name the siblings.

  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 tool is for learning foundational context before using other tools, but it never explicitly states when to choose this over alternatives like 'zone' or 'land_sources'. It lacks a clear when-to-use and when-not-to-use directive, leaving the agent to infer the intended use case from the phrase 'plain-language explanation'.

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

• find_landA
  3.5/5.0
  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 does note that sources are 'free, accessible online' and 'browser-only', and that titles are translated for Cyprus, which is useful. However, it does not disclose potential delays, rate limits, or that results may be incomplete or inconsistent across sources. The mention of 'browser-only sources' hints at limitations but could be more explicit about the need for browser automation or potential unreliability.

  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 relatively concise, with a clear first sentence and a paragraph of examples. It front-loads the core purpose and then gives illustrative cases. However, the line 'Browser-only sources are listed in browser_only_sources' is a bit cryptic and could be clearer. Overall, it is structured well, but there is some repetition of the source list that could be trimmed.

  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 annotations and output schema, the description does a decent job of covering the basics: what it does, sources, filters, and output fields. However, it leaves out important context like the nature of the 'browser-only_sources' (is it a parameter? a tool?), and it does not mention potential errors, rate limits, or how to handle results. For a tool with 7 parameters, this is incomplete but not severely so.

  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 has 7 parameters with 0% description coverage, so the description must compensate. It does not describe each parameter individually, but the examples illustrate how to use 'country' and 'state', and the description mentions filters for price and acreage. Since all parameters are optional and have defaults, this is adequate, but a bit more per-parameter detail would be helpful, especially for 'county' which is not mentioned.

  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: finding land for sale from specific online sources, with optional filters. It also gives examples and mentions the output fields (price, size, location, photos), which helps the agent understand the tool's purpose. It doesn't explicitly contrast with siblings like land_sources, but the verb 'find' and the detail about filtering distinguish it somewhat.

  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 provides usage examples (e.g., find_land(country='CY')) and states the sources, but it does not explicitly say when to use this tool versus alternatives like land_sources or assess_land. The guidance is implied through the examples, but there is no clear 'when not to use' or alternative routing. Given the sibling names, an agent might not know whether to use find_land or land_sources without further context.

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

• zoneA
  3.7/5.0
  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 clearly sets expectations: this is a general guide, not an official source, and it tells the user exactly what to confirm. This is strong transparency about limitations and output nature.

  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 front-loaded with the core purpose and uses a second paragraph for an important caveat. It is compact and every sentence adds value, though slightly longer than strictly necessary.

  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 explainer tool with no output schema and no annotations, the description covers scope, examples, limitations, and what to confirm. It is complete enough for an agent to invoke it correctly and set user expectations.

  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 0%, so the description must compensate. It explains the 'code' parameter via examples and implies the 'country' parameter by listing jurisdictions. However, it does not explicitly define parameter names or the default country, leaving some burden on 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 a specific verb ('Explain') and resource ('planning-zone code') with concrete examples for multiple countries. It does not explicitly name sibling tools, but its scope is distinct enough that an agent can tell it apart from land search/assessment tools.

  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 when to use the tool: when someone needs to understand a zoning code or farm-dwelling conditions. It does not explicitly mention alternatives or when not to use it, though the caveat about not substituting official sources gives some context.

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

• assess_landA
  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 disclosure burden. It enumerates the data sources (Open-Meteo, OpenStreetMap, FEMA), lists the scored dimensions (precipitation, growing season, water access, etc.), and explicitly notes that sources are listed and missing data is flagged. This goes beyond a simple summary and gives an agent reliable expectations about behavior and limitations.

  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 moderately long but each sentence earns its place: purpose, input format, data sources and scoring criteria, and data transparency. It is well front-loaded with the core purpose and avoids redundancy or off-topic 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?

  Given the existence of an output schema, the description does not need to describe the return structure. It covers all essential operational aspects: how to specify the target location, what data sources are used, what criteria are scored, and how missing data is handled. No critical gaps remain for an agent to invoke the tool 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?

  The schema provides no descriptions for lat, lon, or place (0% coverage), so the description must compensate. It clarifies that either place or lat/lon can be used, gives concrete examples ('Petaluma, California' or 'Lamoille County, VT'), and implies that lat/lon are alternatives to place. This adds genuine meaning beyond the raw 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 opens with a specific verb 'Assess' and a resource 'US parcel', then explicitly names the two evaluation outcomes: micro-farming viability and dwelling feasibility. This makes it unmistakable how it differs from sibling tools like 'find_land' (searching for parcels) and 'zone' (zoning rules), which the description naturally distinguishes by focusing on assessment rather than discovery or zoning.

  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?

  It explains how to supply input (place name/address or lat/lon) with examples, which is useful, but does not state when to prefer this tool over siblings or when not to use it. The intended use case (assess a specific parcel) is implied rather than explicitly contrasted with alternatives, so guidance is partial.

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

• land_sourcesA
  4.5/5.0
  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 and does well by consistently describing the tool as read-only ('List') and disclosing the nature of the data (free, keyless, public). This implies no authentication or side effects, though it doesn't explicitly state the response format or that no state changes occur, which is a minor 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?

  A single sentence that front-loads the action, specifies the resource with qualifying attributes, and states the purpose. Every word earns its place with zero 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?

  For a parameterless, output-schema-less informational tool, the description is complete. It tells the agent exactly what information is provided (list of sources), their properties (free, keyless, public), and the rationale (transparency), leaving no obvious gap for correct invocation.

  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 zero parameters, so the schema trivially covers 100% and the baseline is 4. The description adds no parameter-specific information, but none is needed—there is nothing to explain.

  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 action (List), the resource (free, keyless public data sources), and the purpose (transparency). This distinguishes it from siblings like assess_land and find_land, which are operational land tools, making the tool's role obvious.

  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?

  Although it doesn't explicitly contrast with sibling tools, the description makes it clear this is for transparency about data sources, which is distinct from the land-focused actions. The 'transparency' purpose implies usage when a user inquires about data provenance, making the intended context clear without ambiguity.

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