Server Quality Checklist

Tool Scores

• get_camera_imageA
  4.6/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the transparency burden and does well by disclosing the API auth mechanism, the 403 failure mode, and that the tool returns image bytes rather than a URL. It reveals important server-side behavior that an agent would otherwise not know.

  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 front-loaded with the purpose, then provides only essential context about the auth requirement, followed by a brief parameters and returns section. Every sentence contributes meaningful information without 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 single-parameter tool with no output schema, the description fully covers the input meaning, the return value, and why the tool exists. The sibling tools provide camera discovery context, so this description is complete on its own.

  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 coverage is 0%, but the description compensates fully: it explains that asset_id is a Vancam camera asset ID and notes it should be provided as an integer represented as a string. This is exactly the meaning an agent needs 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 and resource: "Get the live frame for a camera by asset_id," clearly distinguishing this tool from sibling camera-listing tools. It also specifies the unique return (live image bytes) and mentions the camera asset ID as input.

  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 explains when this tool is needed: it fetches the frame server-side because a bare URL fetch would result in 403 Forbidden due to the required x-api-key header. This gives clear context for using the tool, though it does not explicitly name alternatives or state exclusions.

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

• get_cameras_by_radiusA
  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 transparency burden. It discloses important behavior such as the maximum radius ('max 50 per API'), the meaning of active_only ('only camera_class=open'), and the JSON return structure ('type radius_search, count, radius_km, cameras[]'). This goes beyond the schema and gives the agent actionable expectations, though it stops short of covering error cases or sorting details.

  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 efficiently structured: a one-sentence summary, a usage line, a parameter list, and a return format. No fluff or redundancy; every section serves a purpose and 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?

  Given the tool's moderate complexity (5 params, output schema present), the description provides complete operational context: purpose, when to use, parameter semantics, and return shape. The output schema covers detailed field structure, so the description need not repeat it, but it still gives a high-level return summary. It is fully adequate for an agent to select and invoke 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 provide parameter meaning. It does so thoroughly: lat/lon identified as center point with WGS84, radius with units/default/max, limit with range/default, and active_only with a clear filter explanation. This fully compensates for the schema's lack of 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?

  Description opens with 'Get traffic cameras within a radius (km) of a lat/lon point,' which clearly states the action, resource, and scope. It distinguishes from sibling tools by focusing on radius-based search, setting it apart from list_cameras or get_nearest_cameras.

  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 when the user asks for cameras near a place, within X km of coordinates, or around an address they geocoded.' This provides clear trigger contexts, though it does not explicitly mention alternatives or exclusions.

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

• get_nearest_camerasA
  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 behavioral traits such as nearest-neighbor search, the active_only filtering (camera_class=open), and the ordering by distance_meters. It does not mention auth or rate limits, but for a read-only query tool these are not critical gaps.

  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 and structured with purpose, usage, parameters, and return sections. Every sentence adds value; the front-loaded purpose and bullet-like parameter list make it easy to scan.

  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 simplicity, four parameters, and an output schema, the description covers all necessary context: when to use, what parameters mean, and what the response contains. The sibling tool names clarify the alternative spatial queries, making the tool complete within its context.

  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?

  All four parameters are explained beyond the schema: lat/lon as query point in WGS84, limit with range 1–100 and default 5, active_only with the meaning of filtering to camera_class=open. Schema coverage is 0%, so this description fully 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 opens with 'Get the nearest traffic cameras to a geographic point,' which clearly states the verb (get), resource (traffic cameras), and scope (nearest to a point). It distinguishes itself from siblings like 'get_cameras_by_radius' and 'get_cameras_along_route' by focusing on nearest-neighbor semantics.

  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 user asks for the closest camera(s) to a location,' providing a clear when-to-use context. It does not list exclusions or alternative tools, but the context is specific enough to guide selection among sibling tools.

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

• list_camerasA
  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 burden. It discloses the return format ('Bounds search JSON with enriched image_url per camera') and the behavior of active_only, adding useful context. It does not mention any side effects, but the operation is inherently read-only.

  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 and well-structured: purpose, usage, parameter list, and return type. Every sentence contributes value, 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 an output schema exists, the description covers all necessary context: purpose, usage, parameters, and return shape. It is complete for a moderately complex tool even without annotations.

  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 coverage is 0%, but the description fully documents all parameters: 'min_lat, min_lon, max_lat, max_lon: Bounding box (WGS84)', 'limit: Max cameras to return (1–100, default 100)', and 'active_only: If true, return only camera_class=open'. This adds complete meaning beyond the bare 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 'List traffic cameras within a map bounding box,' which clearly states the verb, resource, and scope. It distinguishes itself from sibling tools like get_cameras_by_radius by specifying the bounding-box query type.

  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 provides a usage trigger: 'Use when the user asks for cameras in a visible map area or geographic rectangle.' However, it does not mention when not to use or name alternatives directly, though the sibling context implies them.

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

• describe_camera_apiA
  4.7/5.0
  Behavior4/5

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

  Since no annotations are provided, the description carries the full behavioral burden. It discloses that the tool is a documentation/informational tool and specifies the feature set it covers. There is no unsafe or unexpected behavior implied, which is appropriate for a 'describe' tool, though it does not elaborate on response format or side effects beyond the output 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 two sentences, with the first defining the purpose and the second giving usage guidance. It is front-loaded, concise, and contains no filler, making it highly efficient for an agent to parse.

  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 has no parameters and an output schema exists, the description is complete: it states what the tool does, when to call it, and what its documentation covers. The sibling tool names are provided in context, so the agent is well-oriented without missing critical information.

  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 there are no parameter semantics to explain. The baseline of 4 applies, and the description appropriately focuses on use case rather than argument syntax, since the schema is empty.

  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 'Describe the spatial camera API exposed by this MCP server,' giving a specific verb and resource. It distinguishes itself from the sibling search tools by positioning itself as an API reference/entry point, not a searching tool.

  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 phrase 'Call this first when unsure which search tool to use' provides explicit when-to-use guidance. It also clarifies scope by naming the capabilities it documents (bounds pan, radius, route, nearest), which helps the agent decide if this is the right entry point.

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

• get_cameras_along_routeA
  4.7/5.0
  Behavior5/5

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

  With no annotations, the description discloses the straight-line corridor behavior, perpendicular buffer, sorting by route_fraction, and return structure. It also mentions default buffer/limit values and the active_only filtering semantics.

  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?

  Well-structured with a summary, caveat, parameter details, and return section. Slightly redundant with the schema's parameter list, but each sentence contributes and the organization helps scanability.

  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 7-parameter tool with no annotations and a moderate output schema, the description covers behavior, key constraints (straight-line vs driving), result ordering, and output fields. It is complete for an agent to select and invoke 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?

  Adds meaning beyond the schema: WGS84 coordinates, buffer in meters perpendicular to the line, limit range 1–100, and active_only mapping to camera_class=open. Schema only provides names and defaults.

  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?

  Clearly states 'Get traffic cameras along a straight-line route between two points' – a specific verb and resource that distinguishes it from radius/nearest/list tools. The straight-line qualifier is explicit.

  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?

  Notes it mirrors the VanCam route view and explicitly states it uses a straight line, not a driving route polyline. This tells users when to avoid expecting driving-route corridors, though it doesn't name alternative tools directly.

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