Server Quality Checklist

Tool Scores

• search_foodsB
  3.3/5.0
  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 reveals that results include curated 'm*' rows and USDA reference foods and mentions sub-second performance. However, it does not explain what 'm*' means, the result format, or error/empty behavior, leaving notable gaps.

  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 compact and front-loaded with the primary purpose. Each sentence adds information, though the 'HTTP endpoint' detail is somewhat redundant in an MCP context. Overall, it is well-structured and free of fluff.

  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 tool is relatively simple (2 parameters, no output schema), and the description provides the core purpose and return composition. However, it lacks parameter semantics and any indication of the response structure, so the agent may struggle to invoke it correctly and interpret results fully.

  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%, and the description does not mention the 'query' or 'species' parameters at all. The agent must rely on a bare schema with no parameter descriptions, making it impossible to infer parameter meaning or formatting 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 uses the specific verb 'Fuzzy search' and names the resource 'Balance IT's food database.' It also clarifies the result composition (curated 'm*' rows plus USDA reference foods), which clearly distinguishes it from sibling tools like list_catalogue or get_recipe.

  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?

  Usage is only implied: if you need to search for foods, this is the tool. There is no explicit mention of when to use it instead of alternatives, nor any exclusion criteria. Sibling tools are not referenced for differentiation.

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

• calculate_caloriesB
  3.4/5.0
  Behavior2/5

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

  With no annotations, the description carries the full transparency burden. It mentions only 'HTTP endpoint, sub-second,' which adds minor performance/network context, but it does not disclose whether the operation is read-only, has side effects, requires authentication, or how errors are handled. This is a significant gap for a calculation 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.

  Conciseness4/5

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

  The description is two sentences and front-loads the main purpose. The second sentence adds a useful performance/endpoint detail. The phrase 'Balance IT's' is slightly awkward and could be clearer, but overall the description is concise with minimal waste.

  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 6-parameter calculation tool with no output schema, the description is adequate but incomplete. It states the output concept ('daily kcal estimate') but does not specify output format, limitations (e.g., the schema restricts species to canine and feline, yet the description says 'pet' generically), or any caveats. It could benefit from clarifying supported species and return type.

  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 has 0% property descriptions, so the description adds high-level context by naming the key inputs (species, weight, age, reproductive status). However, it does not explain the units, the gender enum meanings, or how parameters relate to each other beyond what the schema already shows. It partially compensates for the low schema coverage but not fully.

  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 that the tool produces a daily kcal estimate for a pet based on species, weight, age, and reproductive status. This specific verb+resource+scope distinguishes it from sibling tools focused on recipes and food searches.

  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 when a calorie estimate is needed given the listed inputs, but it does not explicitly state when to prefer this over alternatives, nor does it mention exclusions or when not to use it. The context is clear but not prescriptive.

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

• get_recipeA
  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. It adds behavioral context by noting 'Browser-driven' and '~5-10s' latency, which are useful traits. However, it does not disclose whether the operation is read-only, what happens on missing recipe, or whether it requires any existing session, leaving several behavioral aspects unstated.

  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, information-dense sentence plus a short latency note. It avoids redundancy and front-loads the core action and output data, making it efficient and easy to parse.

  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 simplicity (one parameter, no output schema), the description provides a reasonable overview of inputs and expected outputs. It lists the key data points returned but does not specify format or error handling. Since no output schema exists, a bit more detail on the return structure would improve completeness, but the current level is adequate for a simple fetch tool.

  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 defines option_id as a string, but the description embeds it in the URL /recipe/<option_id>, giving it clear semantic meaning as the built recipe identifier. Since schema description coverage is 0%, the description compensates well by explaining how the parameter is used, though it does not enumerate possible values or origins.

  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 loads /recipe/<option_id> and extracts specific data (calories, macro split, gram-weight ingredient list, required supplement), using a specific verb 'load' and 'extract'. This distinguishes it from siblings like generate_recipe (generates) and calculate_calories (calculates), making its purpose unambiguous.

  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 for retrieving details of a built recipe, but it does not explicitly state when to use this tool versus alternatives like generate_recipe or list_catalogue. It also does not mention preconditions such as needing an existing recipe id or a live browser session, leaving usage context somewhat implied rather than explicit.

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

• list_catalogueA
  4.2/5.0
  Behavior4/5

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

  No annotations exist, so the description carries the burden. It discloses that results are cached for 7 days and that the tool is browser-driven with a 5-8s first call, which are useful behavioral insights beyond a basic list operation.

  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?

  Three sentences, front-loaded with the core purpose, and every sentence adds value: complete catalogue, cache duration, and latency expectation. No wasted words.

  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?

  With no output schema, the description covers purpose, parameters, caching, and performance, which is solid for a simple list tool. It lacks details about the return format or potential pagination, but the information provided is sufficient for basic 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?

  Schema description coverage is 0%, but the description adds meaning by giving item counts for canine adult (79) and noting 51 are one-pot-compatible. This partially explains the 'species' and 'one_pot_only' parameters, though it does not cover all enum values.

  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 lists the complete ingredient chip catalogue for a species, using a specific verb and resource. It distinguishes itself from sibling tools by emphasizing 'full catalogue' versus recipe generation, calorie calculation, or food search.

  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?

  Usage is implied: it is for retrieving the complete catalogue for a species, but no explicit when/when-not guidance or mention of alternatives is given. The description does not state 'for filtered search use search_foods' or similar exclusions.

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

• session_statusA
  4.2/5.0
  Behavior3/5

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

  With no annotations, the description must carry behavioral transparency. It states the tool checks for a session 'on disk' which adds useful context about side-effect-free inspection. However, it does not clarify what 'usable' means, how the result is returned (e.g., boolean, object), or whether any network/auth is involved. This is minimal but not misleading.

  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 concise sentences: the first states the core function, the second adds usage guidance. No wasted words, front-loaded with the most important information. This is ideal for a simple status-check tool.

  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 low complexity (0 params, no output schema), the description is fairly complete. It covers what it does and when to use it, implying a boolean result via 'Whether.' It does not specify the exact output format or session validity criteria, but for a simple check this is acceptable.

  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, and schema description coverage is 100% (empty schema). The baseline for 0 params is 4. The description adds no parameter details because none exist, but it gives enough context about what the tool evaluates.

  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: checking whether a usable balance.it session exists on disk. This is a specific verb+resource combination that distinguishes it from recipe/calorie sibling tools. The title 'Report persisted session status' aligns with the description.

  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 gives usage context: 'Useful to distinguish "dead session" from "real failure" before running slower tools.' It indicates when to use this tool (as a pre-check) and implies an alternative (slower tools). It lacks an explicit 'when not to use' but the context is clear enough.

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

• generate_recipeA
  4.7/5.0
  Behavior5/5

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

  With no annotations provided, the description carries the full burden of disclosure. It reveals that the tool is 'Browser-driven; typically 60-90s,' explains the response fields (submitted_food_ids and missing_from_options), and clearly states error behavior: 'Any food_id that could not be added throws a clear error rather than silently dropping.' This is exceptional 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 concise and front-loaded, starting with the action, then providing latency, input provenance, response details, and error behavior in four sentences. Every sentence adds essential 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?

  Despite having 10 parameters, no output schema, and no annotations, the description covers the workflow, expected latency, key response elements, and error handling. It gives a user enough context to use the tool correctly and set expectations, making it highly complete for its complexity.

  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?

  Schema description coverage is 0%, so the description must compensate. It adds meaning by explaining the workflow, that food_ids come from other tools, and that N options are built. However, it does not describe all parameters (e.g., one_pot_cooking, weight_unit, age_unit) beyond the schema's enum names, leaving some gaps.

  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: 'Fill the pet profile, pick ingredient food_ids, submit, and wait for Balance IT to build N balanced recipe options.' It uses a specific verb (build) and resource (balanced recipe options), and distinguishes itself from siblings like search_foods, list_catalogue, and calculate_calories by focusing on recipe generation.

  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 usage context by stating 'Food_ids come from search_foods or list_catalogue,' which tells the user how to obtain necessary inputs. It implicitly defines the use case (generating recipes) without explicitly naming alternatives, but the integration with other tools gives practical guidance.

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