Server Quality Checklist

Tool Scores

• call_toolA
  3.7/5.0
  Behavior2/5

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

  No annotations are provided, so the description must carry the transparency burden. It clearly states the dispatch operation but does not disclose potential side effects of arbitrary tool execution, error behavior for unknown tool names, or argument validation requirements. It does mention discovered tools as a boundary, but lacks safety/behavioral warnings.

  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-loads the action, and contains no filler. Every phrase contributes to understanding the tool's purpose and usage.

  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 generic dispatcher with 2 parameters and no output schema, the description plus schema are minimally usable. However, it lacks mention of what happens after execution (e.g., return of the nested tool's result) and does not specify that arguments must conform to the called tool's schema. The search_tools context partially compensates but doesn't fully cover these 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?

  The input schema already covers 100% of the parameters, naming both 'name' and 'arguments' with descriptions. The description adds no parameter details beyond 'given arguments,' so the schema-based baseline of 3 is appropriate. Additional guidance about aligning arguments with the target tool's schema would improve this score.

  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 'Call a tool by name with the given arguments,' which is a specific verb plus resource. It also says 'Use this to execute tools discovered via search_tools,' distinguishing this execution tool from sibling discovery/resource/prompt tools.

  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 second sentence explicitly guides the agent to use call_tool after search_tools discovers a tool. It implies the execution role of the tool relative to discovery, though it doesn't explicitly exclude resource/prompt tools or state when not to use it.

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

• list_promptsA
  4.2/5.0
  Behavior3/5

  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 states that the tool returns JSON metadata, which is useful, but it does not explicitly state that this is a read-only operation with no side effects, nor does it mention any limitations like pagination. For a simple list operation, this is adequate but not rich.

  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 terse sentences: the first delivers the primary action, the second clarifies the return format. Every word earns its place, with no redundancy or irrelevant detail.

  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 zero-parameter tool with an existing output schema, the description covers the essential purpose and return type. It is complete, but could be slightly more helpful by explicitly connecting to get_prompt for retrieving specific prompts, which would aid discoverability.

  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 description does not need to explain parameter meaning. The description adds a small amount of value by mentioning that the output includes 'optional arguments', but per the guideline, 0 params warrants a baseline score of 4.

  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') and the resource ('all available prompts'), making the purpose unambiguous. It also distinguishes from siblings like list_resources by specifying prompts, and from get_prompt by listing rather than retrieving a specific prompt.

  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 the tool: to enumerate all available prompts. It does not explicitly mention alternatives or exclusions, but the context is clear for a list operation with no parameters. A brief note on using it before get_prompt would elevate this to a 5.

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

• search_toolsA
  4.3/5.0
  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 key behavioral traits: the search returns matching tool definitions, ranked by relevance, and formatted identically to list_tools. This goes beyond the obvious by specifying the ranking behavior and return format. While it doesn't explicitly state it's a read-only operation or discuss errors, those are implied for a search function and the description provides sufficient transparency for a non-mutating 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 exactly two concise sentences, front-loaded with the purpose. It includes the essential details (natural language search, relevance ranking, format) without any fluff or repetition. Every sentence earns its place, making it highly efficient.

  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 simple one-parameter tool with an output schema present (which presumably defines the return format), the description is complete. It explains what the tool does, how results are ordered, and that the format matches list_tools. There are no complex edge cases or prerequisites to document, so no meaningful context is missing.

  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 already describes the only parameter, query, as 'Natural language query to search for tools' (100% coverage). The description repeats 'natural language' without adding any new meaning about query syntax, examples, or constraints. Baseline 3 applies because schema coverage is high and the description adds no additional parameter semantic value.

  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 'Search for tools using natural language,' which identifies the specific verb (search) and resource (tools). It distinguishes from siblings like call_tool, list_resources, and read_resource by focusing on searching rather than executing or accessing. The addition of 'ranked by relevance' and 'in the same format as list_tools' further clarifies its unique function.

  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 you need to find tools via natural language rather than listing all tools. It references list_tools for format, indirectly contrasting with a full list. However, it doesn't explicitly mention when not to use it or name alternatives, so it earns a 4 rather than a 5.

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

• get_promptA
  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 behavioral transparency burden. It explains the return format (JSON with a messages array) and clarifies how arguments should be structured (dict mapping names to values). It does not cover error cases or side effects, but for a simple get operation 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 two sentences, front-loaded with the primary action ('Get a prompt by name'), followed by concise return-format and argument-format details. Every sentence adds value with no redundancy or 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 tool has only two parameters, an output schema, and no annotations, the description covers the essential behavioral aspects: what it retrieves, how to pass arguments, and what the return shape looks like. It is sufficiently complete for an agent to invoke the tool correctly without further context.

  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 already provides descriptions for both parameters (name and arguments), giving 100% coverage. The description adds extra meaning by specifying that arguments must be a dict mapping argument names to values, which is not fully detailed in the schema. This elevates the score above the baseline.

  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 a prompt by name, with optional arguments. This distinguishes it from sibling tools like list_prompts (which would enumerate prompts) and call_tool (which invokes tools). The verb-resource pair is 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 implies when to use this tool: when you know the prompt's name and want its rendered output. It does not explicitly mention alternatives or provide 'when not to use' guidance, but the context is clear enough for an agent to decide appropriately.

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

• list_resourcesA
  4.5/5.0
  Behavior4/5

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

  The readOnlyHint annotation already communicates safety, and the description adds valuable behavioral context by explaining the return shape: static resources have a 'uri' field, templates have a 'uri_template' field with placeholders. This goes beyond the annotation without contradicting it, though it could mention pagination or ordering if applicable.

  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 the main purpose, and every sentence adds meaning. It briefly explains the output distinction without unnecessary 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 tool's simplicity, the presence of an output schema, and the readOnly annotation, the description is complete. It covers the resource types, the return format, and the template placeholder pattern, leaving no critical gaps.

  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 zero parameters, and the baseline for no parameters is 4. The description does not need to explain parameter semantics because there are none, and the resource-return details are more relevant.

  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 a specific verb and resource: 'List all available resources and resource templates.' It clearly identifies the scope (all resources) and distinguishes from siblings like read_resource, which implies retrieving a specific resource, and list_prompts, which targets a different resource 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?

  The phrasing 'List all available resources and resource templates' clearly communicates when to use this tool: when you need an enumeration of resources. It lacks explicit exclusion or alternative references, but the context is unambiguous, and the sibling tool names (read_resource, list_prompts) reinforce the intended use.

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

• read_resourceA
  4.7/5.0
  Behavior5/5

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

  The description discloses that content is returned as a string and that binary content is base64-encoded, which is valuable behavioral context beyond the readOnlyHint annotation. It also clarifies the templating behavior, adding transparency about expected URI formats.

  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, using three sentences that each add value: the first states the core action, the second clarifies URI formatting, and the third explains the return format. No unnecessary words or repetition.

  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 (one parameter, readOnlyHint, output schema present), the description covers the essential information: what it does, how to construct the URI, and what to expect in the response. It is complete for an agent to select and 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 only says 'The URI of the resource to read', but the description enriches this by explaining the distinction between static and templated URIs and how to fill in template parameters. This goes beyond the schema's bare parameter 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 uses a specific verb ('Read') and clearly indicates the resource type ('a resource') and the method ('by its URI'). It distinguishes from siblings like list_resources and get_prompt by focusing on reading a single resource via URI.

  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 provides explicit instructions on how to format URIs for static versus templated resources, which is useful guidance. However, it does not explicitly contrast this tool with alternatives like list_resources or get_prompt, leaving 'when to use' somewhat implied.

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