Server Quality Checklist

Tool Scores

• get_employee_summaryA
  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 carries the full burden. It transparently describes the return contents and implies a read-only database lookup via 'Get' and 'Returns.' However, it does not address potential permission requirements, data freshness, or any side effects; this is adequate for a simple summary getter but not especially 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 extremely concise and front-loaded: two sentences, the first stating the main action and the second listing the returned data. Every sentence adds value and there is no redundancy.

  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 read summary with an output schema present, the description covers the purpose and key return fields. It lacks explicit sibling differentiation and usage caveats, but given the low complexity and supporting output schema, it is reasonably complete.

  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 accepts zero parameters, so there are no parameter semantics to clarify. The baseline of 4 applies because the schema has no parameter burden for the description to supplement.

  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 'Get' with a clear resource: 'employee and company information from the database.' It enumerates exact return fields (name, fiscal code, hire date, role) and the number of payslips, which clearly distinguishes it from sibling tools focused on salary history, payslip details, or payslip search.

  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?

  There is no guidance about when to use this tool versus the sibling tools, no explicit alternatives, and no exclusions. The description is purely functional and does not help an agent decide between this and get_salary_history_tool, get_payslip_details_tool, or search_payslip_items.

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

• get_payslip_details_toolA
  3.9/5.0
  Behavior3/5

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

  With no annotations, the description must carry the transparency burden. It discloses the return structure (master record plus line items with examples like base pay, overtime, taxes), which is useful. However, it omits any mention of side effects (though 'get' implies read-only), error behavior, or dependency on employee context. It adds some value but not full 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 well-structured: a one-sentence purpose, an Args list, and a Returns summary. Every sentence earns its place with no redundant content.

  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?

  The tool is simple (2 params, no nested objects) and has an output schema, so the description need not detail every return field. It provides an adequate summary of the return payload and clearly defines inputs. Minor gaps: it does not explain how the employee is determined or what happens if no payslip matches, but for this complexity, it is mostly complete.

  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 compensate. It fully does so: 'mese: Month number (1-12)' and 'anno: Year (e.g. 2026)' provide both meaning and format for the two parameters, which the schema only lists as integers with titles.

  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: 'Get the full details of a specific payslip by month and year.' It specifies the verb (Get), the resource (payslip), and the scope (specific, by month/year), which distinguishes it from siblings like get_employee_summary (aggregate) and search_payslip_items (search).

  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. It does not mention exclusions, preconditions, or sibling tools like search_payslip_items or get_salary_history_tool. The context signals include siblings, but the description itself provides no usage direction.

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

• ingest_payslipsA
  4/5.0
  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. It discloses deduplication via SHA-256 and the return summary structure. However, it does not mention potential issues like invalid PDF handling or permission requirements, though the core write behavior is clear.

  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 main action, and includes essential behavioral details without any filler. Highly concise and well-structured.

  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 one-parameter tool, the description covers the process, deduplication, and return summary. Since an output schema exists, return values are explained elsewhere. Minor gaps exist around error handling or file format specifics, but overall it is sufficiently 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?

  The description adds meaning by stating the parameter is the directory to scan for PDFs, which goes beyond the schema's raw title. However, it does not specify whether the scan is recursive, path constraints, or other details, so compensation is only partial.

  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 scans a directory, parses PDF payslips, and stores them in the database. It uses specific verbs and resources and is distinct from sibling tools that are all query operations.

  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 purpose clearly implies when to use this tool (for ingesting payslips), but there is no explicit statement about when to use it vs alternatives. Sibling tool names suggest they are for querying, yet no alternatives are referenced directly.

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

• search_payslip_itemsA
  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 carries the full burden. It discloses the SQL LIKE matching mechanism, the grouping/summation behavior, and the return format (per-month breakdown and grand totals), which is substantial behavioral detail. It does not discuss edge cases or explicit read-only status, but the search nature implies it.

  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 well-structured: a one-line summary, a brief technical explanation, an Args list, and a return statement. Each sentence adds value with no redundancy. Front-loaded with the most important information.

  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 tool with three simple parameters and an output schema, the description covers the search behavior, parameter semantics, and return shape. It omits minor edge cases (e.g., behavior with no results), but overall it provides sufficient context for correct invocation.

  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?

  The input schema provides only type and default information, with zero semantic descriptions. The description's 'Args' section adds meaningful detail: keyword examples ('Straordinario', 'Ferie'), start_year as a 'from' filter, and end_year as an 'up to' filter. 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?

  The description clearly states the tool's function with a specific verb ('Search') and resource ('payslip line items by description keyword'). It also mentions the underlying table and matching method, distinguishing it from siblings like get_payslip_details_tool.

  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 explains what the tool does (searches by keyword, groups by month/year) but does not explicitly state when to use it versus alternatives. No exclusions or comparison with sibling tools are mentioned, leaving usage guidance implied.

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

• get_salary_history_toolA
  4.5/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the burden of behavioral disclosure. It discloses ordering (most recent first), optional filters, and the exact list of returned fields, giving a transparent view of the tool's output and basic behavior. It doesn't discuss edge cases or error handling, but for a simple read-style query this is strong.

  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, front-loaded with the purpose, and every sentence adds meaningful information. The Args/Returns structure is standard and immediately parseable, with no wasted words.

  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?

  Even though an output schema exists, the description thoroughly covers the tool's behavior, parameters, ordering, and return shape. For a simple two-parameter retrieval tool, this is complete and leaves no major ambiguity.

  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 has zero descriptions, so the description is the sole source of parameter meaning. It explains 'year' as an optional filter and 'limit' as the max months with default 12. This adds semantic value beyond the raw type/default fields in the 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 starts with a specific verb+resource: 'Get salary history' ordered by most recent month first. This clearly distinguishes the tool from siblings like get_payslip_details_tool or search_payslip_items, which focus on individual payslips or searching items.

  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 establishes clear context (retrieving salary history by month) and mentions optional year filtering and limit, but does not explicitly compare with sibling tools or state when not to use it. This is 'clear context, no exclusions' per the rubric, so a 4 is appropriate.

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