Server Quality Checklist

Tool Scores

• add_expenseC
  2.4/5.0
  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 of behavioral disclosure. It states the tool creates a new entry (implying mutation) but doesn't reveal whether entries are editable/deletable afterward, how duplicates are handled, whether any validations apply to fields like amount or date, or what the response confirms. For a write operation with zero annotation coverage, this is a meaningful gap.

  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 single-sentence description is efficient with zero wasted words. It's appropriately short for the overall tool. However, the brevity crosses over into under-specification given the 5 parameters and 0% coverage, so while concise it doesn't fully earn its brevity.

  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?

  For a tool with 5 parameters, 0% schema coverage, no annotations, and no output schema, the description is severely incomplete. It provides no field format guidance, no return behavior, no error conditions, and no validation rules. A more robust description is warranted for a mutation tool of this complexity.

  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%, meaning the description must compensate for the 5 undocumented parameters. The description names 'expense entry' but doesn't explain the format of date, amount, category, or the semantics of note and subcategory beyond their schema titles. Parameters like date (expected format?) and amount (currency? negative allowed?) are entirely unexplained.

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

  Purpose3/5

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

  The description 'Add a new expense entry to the database' has a clear verb ('Add') and resource ('expense entry'), establishing the tool's core purpose. However, it doesn't differentiate from sibling tools like list_expenses or summarize effectively beyond the obvious add-vs-query distinction, and it lacks any detail about what an 'expense entry' comprises.

  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 given on when to use this tool versus alternatives. While the add-vs-list/summarize distinction is somewhat implicit in the name, the description doesn't state prerequisites, what category values are valid, or whether existing entries should be checked first. There are no explicit when-to-use or when-not-to-use instructions.

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

• summarizeC
  2.4/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries full burden of behavioral disclosure. It doesn't state whether this is read-only, whether it includes subtotals/totals, how the category grouping behaves when category is null (all categories or ungrouped), or what the output shape looks like. For an aggregation tool, these behavioral details matter significantly.

  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?

  Single sentence, zero filler. It front-loads the verb and key info efficiently. However, given the 0% schema coverage and ambiguous category parameter, some additional explanation would be justified despite the good conciseness.

  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?

  A summarize/aggregate tool with no output schema, no annotations, 0% schema coverage, and an ambiguous category parameter is under-explained. The description leaves the agent uncertain about output format, category behavior, and how it differs from list_expenses. For an aggregation tool with these gaps, more context is needed.

  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%, so the description must compensate. It explains the purpose of start_date/end_date semantically ('inclusive date range') which is useful, but the 'category' parameter is entirely unexplained—its default null and meaning (filter vs grouping key) are ambiguous. The description mentions 'by category' but doesn't clarify whether category is required for the summary, optional filtering, or how null behaves.

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

  Purpose3/5

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

  The description states a clear verb+resource+scope: 'Summarize expenses by category within an inclusive date range.' It distinguishes from siblings (add_expense creates, list_expenses lists), and 'summarize' implies aggregation rather than raw listing. However, it doesn't explicitly name alternatives or clarify how summarize differs in output from list_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 explicit guidance on when to use this vs list_expenses. The verb 'summarize' implies grouping/aggregation, and 'by category' hints at the grouping dimension, but there's no clear when-to-use/when-not-to-use guidance or mention of alternatives. Sibling tools suggest this is meant for aggregated views, but that's only implied.

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

• list_expensesB
  3.2/5.0
  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 of behavioral disclosure. 'Inclusive date range' clarifies boundary handling usefully, and it's implicitly a safe read. However, it doesn't disclose return format, pagination, ordering, maximum range, or filtering capabilities—gaps for a data-listing tool without annotations.

  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?

  Single sentence, zero wasted words, front-loaded with the main verb and object. Efficient and readable for the purpose it sets out to achieve, though brevity borders on under-specification.

  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 simple (2 flat params, no output schema, no nested objects), so it doesn't demand a lot. The description covers the core purpose and boundary semantics. However, given 0 annotations and 0% param coverage, more detail about date format and return shape would improve completeness for an agent with no other signal source.

  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 states the range is inclusive but provides no format guidance (e.g., date syntax), meaning both start_date and end_date have minimal semantics beyond their names. The inclusive-range note adds modest value, but an agent still needs to guess supported date formats.

  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 'List expense entries within an inclusive date range' uses a specific verb (list) with a clear resource (expense entries) and communicates scope (date range, inclusive). It distinguishes from siblings: add_expense (a write) and summarize (aggregation) are clearly different operations, though the description doesn't explicitly differentiate.

  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?

  The description implies use when a date range is known, but offers no guidance on when to choose this vs summarize, how far back data is available, or edge cases like empty ranges. No exclusions or alternative tool references are given, so an agent gets limited direction on contextual selection.

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