Server Quality Checklist

Tool Scores

• add_expenseC
  2.6/5.0
  Behavior2/5

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

  With no annotations provided, the description carries the full burden, but it only says 'Add an expense' without disclosing behavioral traits such as required fields, side effects, idempotency, or potential validation rules.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness3/5

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

  The description is concise and front-loaded, but it is under-specified rather than appropriately sized for a tool with five parameters and no annotations.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness1/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given no annotations, no output schema, and a minimal description, the tool is inadequately documented. Details about parameters and behavior are entirely missing, making it impossible for an agent to invoke it correctly in complex scenarios.

  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 has 0% description coverage for its five parameters, and the description adds no meaning beyond the parameter names. It does not explain what 'price' represents, how 'category' is used, or the purpose of optional fields like 'date_added'.

  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 ('Add') and the resource ('expense'), which distinguishes it from sibling tools like read_expenses, summarize_expenses, and filter_by_category that have different purposes.

  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 is provided on when to use this tool versus the sibling tools. It does not mention any prerequisites, context, or exclusions for adding an expense.

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

• filter_by_categoryA
  3.6/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the burden. It indicates a read operation via 'get', but lacks details on ordering, pagination, error behavior, or explicit read-only confirmation. The verb provides some transparency but not rich context.

  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?

  Single sentence, front-loaded, concise, with no unnecessary words. Every word contributes to the core purpose.

  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 one-parameter read tool with an output schema, the description covers the core purpose adequately. It lacks usage guidance and parameter detail, but given the simplicity, it is mostly complete.

  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 has one parameter 'category' with 0% description coverage. The description adds meaning by showing category is the filter criterion, but doesn't clarify accepted values, matching rules, or format beyond the parameter name.

  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 states 'Get all expenses for a specific category' – a clear verb (get), resource (expenses), and scope (category filter). This distinguishes it from siblings like read_expenses (likely all expenses) and summarize_expenses.

  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 vs alternatives; no mention of using it instead of read_expenses for category-specific queries. Only implicit usage via the phrase 'for a specific category'.

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

• summarize_expensesA
  3.8/5.0
  Behavior3/5

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

  No annotations are provided, so the description must carry behavioral context. It conveys a read-only 'get' operation and specifies a date range, but does not explicitly confirm read-only status, side effects, or error behavior. The verb 'get' strongly implies safety, yet the disclosure is minimal.

  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?

  One sentence of 12 words with crucial information front-loaded ('Get total expenses'). It includes necessary details (date range and ISO format) without unnecessary elaboration.

  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 tool with two parameters and an existing output schema, the description sufficiently covers purpose and input semantics. It lacks guidance on alternative tools, but the basic usage is unambiguous for a straightforward aggregation task.

  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 descriptions cover 0% of parameters, but the description compensates by naming both start_date and end_date, specifying ISO format, and clarifying their relationship as a range. This adds meaning beyond the bare schema type declarations.

  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 'Get total expenses between start_date and end_date' clearly states a specific verb + resource and indicates aggregation. It distinguishes the tool from siblings like read_expenses (listing) and filter_by_category (categorizing) by focusing on total calculation.

  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 when-to-use guidance, exclusions, or mention of alternatives among sibling tools. The description implies usage for obtaining a summed amount over a date range but does not clarify when to prefer this over read_expenses or filter_by_category.

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

• read_expensesA
  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 itself must convey behavior. It clearly states this is a read operation, which is inherently non-destructive. The 'all' scope shows the extent of data returned. While no additional details like ordering or pagination are given, the output schema covers return structure, making this sufficient for a simple read 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 three words: 'Read all expenses'. It is maximally concise, front-loaded with the verb and resource, and every word contributes meaning. There is 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 simple, parameterless read tool with an output schema, the description is complete. It states the action and scope, and the output schema handles return value documentation. No further details are necessary.

  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 already fully documents them. The description adds no parameter-specific information, but there is nothing to add. Baseline for zero parameters is 4, and the description is adequate.

  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 'Read all expenses' uses a specific verb ('Read') and resource ('expenses') with an explicit scope ('all'). It clearly differentiates from siblings like filter_by_category and summarize_expenses, which imply filtering and aggregation respectively.

  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 phrase 'all expenses' implicitly tells when to use this tool (when the full list is needed), but it does not explicitly mention alternatives or when not to use it. There is no direct comparison to sibling tools, so the guidance is 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.