Server Quality Checklist

Tool Scores

• list_maps_placesC
  2.9/5.0
  Behavior2/5

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

  No annotations are provided, so the description bears full responsibility for disclosing behavior. It implies a read-only listing but never explicitly states safety, side effects, or what happens if output_dir is invalid. This gap is significant for a tool with no annotation guidance.

  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 core purpose ('List previously fetched places') and adds supplemental details (counts, metadata). Every word contributes to understanding.

  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?

  With a defined output schema, return values need not be described, but the description omits critical operational context such as whether output_dir is required, its default behavior, or any expected directory structure. The tool is simple, but the lack of parameter clarity and usage guidance reduces completeness to a marginal level.

  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%, and the description only hints at 'output root' without explicitly tying it to the output_dir parameter. It does not explain the format, defaults, or constraints of output_dir, leaving the agent to guess its meaning.

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

  Purpose4/5

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

  The description clearly states the verb 'List' and the resource 'previously fetched places', and specifies it includes photo/video counts and metadata. It distinguishes itself from siblings like fetch_maps_place (which fetches new places) by emphasizing 'previously fetched'.

  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 on when to use this tool versus alternatives like get_place_info or get_place_media. It does not mention exclusions or preconditions, leaving the agent to infer that it is for browsing accumulated results without explicit direction.

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

• get_place_infoA
  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 full responsibility for behavioral disclosure. It clearly states 'No media downloaded' (a key side-effect avoidance) and emphasizes 'metadata-only' fetch, implying a read operation. The time estimate (~20-40s) adds performance context. While it does not mention error handling, pagination, or rate limits, the explicit 'no media' behavior and simplicity of the operation justify a 4.

  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, consisting of two sentences. The core purpose and key differentiator ('No media downloaded') are front-loaded, and the use condition is clearly stated. Every sentence adds value; the time estimate is optional but not wasteful. It is appropriately sized for the tool's simplicity.

  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?

  Despite having an output schema, the description lacks essential context for calling the tool correctly. The 'output_dir' parameter is unexplained, and there is no clarification on the URL format or the tool's scope (e.g., whether it returns a single place or handles multiple). The exclusion of annotations and 0% schema descriptions place the burden on the description, which it only partially meets. The description is adequate for a basic call, but the ambiguity around output_dir and input expectations makes it incomplete.

  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?

  Schema description coverage is 0%, so the description must explain the parameters. It fails to do so: it does not mention that 'url' is the required input or what it should contain (e.g., a Google Maps URL), and 'output_dir' is completely unexplained—its purpose is ambiguous despite a default value. The description lists returned fields but provides no guidance on how to set parameters, leaving the agent without sufficient context.

  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 metadata-only business info and lists exact fields (name, phone, website, rating, address, plus code, hours, coordinates). The phrase 'No media downloaded' explicitly differentiates it from the media-focused sibling, and the use-case ('only needs business info') further distinguishes it. The verb 'fetch' plus specific resource makes it 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 provides a clear condition for use: 'Use when the agent only needs business info.' It also implies when not to use (e.g., when media is needed) by stating 'No media downloaded.' However, it does not name alternative sibling tools or explicitly contrast with fetch_maps_place or list_maps_places, so it lacks a fully explicit routing guidance.

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

• get_place_mediaA
  3.9/5.0
  Behavior3/5

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

  Annotations are absent, so the description must carry the disclosure burden. It does mention that it downloads media and returns output directories, implying file writes, but it does not disclose authentication requirements, potential failure modes, or whether the operation is read-only (it likely is). The description provides some transparency but not full behavior context for a tool with no annotation support.

  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 extremely concise: the purpose and usage are stated in the first two sentences, and the Args section is a compact, structured list. No fluff, no redundancy. It is efficiently front-loaded and easy to parse.

  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 tool with 3 parameters and an output schema, the description covers the core purpose, usage, and kind parameter. However, it leaves gaps: output_dir is never explained, error handling is absent, and side effects (file writes) are only hinted at via 'output dirs.' Given no annotations, the tool would benefit from a bit more detail to be fully complete for an agent.

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

  Parameters3/5

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

  Schema description coverage is 0%, so the description must compensate. It explains the 'kind' parameter with its allowed values and default. However, it does not explain 'url' (though semantically obvious from the tool name) or 'output_dir' (implied from the return value but not explicitly defined). The partial coverage is useful but incomplete for the undocumented 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 clearly states a specific action: downloads gallery photos and/or videos, and explicitly frames it as 'media-only fetch' that skips verbose metadata. This distinguishes it from siblings like get_place_info (metadata) and fetch_maps_place (generic fetch), so an agent can tell it apart instantly.

  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 when the agent only needs the images/videos,' which gives a clear condition for selection. It does not name alternative tools explicitly, but the framing implies that for metadata or other data, other tools should be used. This is clear context, though it could be improved by naming exact siblings.

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

• fetch_maps_placeA
  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 full burden. It discloses that it downloads at 'max resolution', creates a subfolder with specific files, returns a JSON summary, and provides typical run times. It also notes the deprecated meta_only alias. This is transparent about core behavior. It omits edge cases like invalid URLs or missing media, but the essential behavioral traits are well covered, so a 4 is appropriate.

  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 well-structured with a clear first sentence for purpose, followed by an Args list, and then return/timing info. The inclusion of a very specific default path ('/mnt/d/Projects/maps-data-fetcher/places') is an implementation detail that may not be relevant to an agent, slightly reducing conciseness. Overall, it is efficient and front-loaded, but not perfectly lean.

  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 tool's complexity, absence of annotations, and presence of an output schema, the description covers all essential aspects: what the tool does, input requirements, behavior (downloads, creates files), output format, and performance expectations. It even documents the deprecated alias. The existence of the output schema excuses the lack of detailed return structure. No critical information is missing for an agent to call it correctly.

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

  Parameters5/5

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

  Schema description coverage is 0%, so the description must compensate. It does so thoroughly: each parameter (url, output_dir, include, meta_only) is documented with types, defaults, and allowed values. The include parameter's options are enumerated, the output_dir default is given, and meta_only's deprecated status is noted. This adds substantial meaning beyond the bare schema, fully compensating for the lack of schema descriptions.

  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 explicitly states the verb ('Fetch a Google Maps place by link'), the resource (a Google Maps place URL), and the scope (downloads media and metadata). It clearly distinguishes itself from siblings by combining both info and media in one call, and it lists the exact metadata fields and media types. An agent can understand exactly what this tool does and how it differs from get_place_info or get_place_media.

  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 gives clear context on the input format ('single place only, not search links') and the include parameter allows partial fetches, which implies alternative usages (e.g., 'info' only). However, it does not explicitly name alternative tools or state when to prefer a sibling over this one. The guidance is implied through the include options rather than stated as a routing decision, so it scores at the 'implied usage' level.

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