Server Quality Checklist

Tool Scores

• list_excel_sheetsA
  3.8/5.0
  Behavior3/5

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

  No annotations are provided, and the description does not disclose any behavioral details beyond the primary read operation. It does not mention authentication requirements, side effects, or error conditions. However, for a simple list operation, the behavior is self-evident, so this is adequate but not comprehensive.

  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 one sentence, front-loaded with the verb and resource, and contains no unnecessary 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?

  The tool is simple with three optional parameters and no output schema. The description explains the primary function and implies the return of worksheet names. It does not explicitly describe the output format or the requirement to supply either link or driveId/itemId, but these are covered in the schema. Overall, it is sufficient for a basic list operation.

  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 provides 100% coverage of the three parameters with clear descriptions. The tool description adds no additional parameter semantics beyond the schema, so a baseline score of 3 is appropriate.

  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 identifies the action (list) and the resource (worksheet names in a SharePoint-hosted Excel workbook), distinguishing it from sibling tools like describe_sheet or get_cell_range.

  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 caller needs worksheet names, but it does not explicitly state when to prefer this over resolve_link or describe_sheet, nor any exclusions. The usage context is clear from the purpose, so an agent can infer when to call it.

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

• resolve_linkA
  4.2/5.0
  Behavior4/5

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

  With no annotations, the description carries the burden of behavioral disclosure. It adds valuable context: links can expire/be revoked, resolving costs a round trip, and the returned IDs are stable. It doesn't cover failure modes or auth requirements, but the key behavioral traits are disclosed, exceeding a bare description.

  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?

  Two sentences, front-loaded with the core purpose, then a succinct rationale for reuse. No fluff or redundancy; every sentence adds value.

  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 with no output schema, the description is quite complete: it explains the input, output, and usage context. It could mention error handling (e.g., invalid link) but is otherwise coherent and sufficient.

  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 description for 'link' is 100% covered ('SharePoint sharing link or direct document URL'). The description reinforces this and adds the purpose of stable IDs, but it doesn't provide format examples or constraints beyond the schema. Baseline of 3 is appropriate as the schema already documents the parameter.

  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 verb 'Convert' and the resource 'SharePoint sharing link or document URL' into 'driveId/itemId values'. This is specific and distinguishes it from sibling tools like list_excel_sheets or get_cell_range, which focus on sheet operations.

  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 says 'Call this once and reuse the IDs' and explains why (links can expire, extra Graph round trip). This is clear usage guidance, though it doesn't mention explicit exclusions or alternatives. However, given the unique purpose, this is sufficient.

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

• get_permission_matrixA
  4.4/5.0
  Behavior4/5

  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. It explicitly discloses a non-obvious performance behavior: 'maxRows/offset/filter/columns are applied AFTER the full sheet is fetched.' This adds significant context beyond the schema and helps the agent anticipate resource usage.

  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?

  Two sentences, both essential. The first states the core purpose; the second provides crucial behavioral guidance. No filler or redundancy. The most important caveat is front-loaded in the second sentence.

  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 9 parameters and no output schema, the description covers the core purpose, return shape (structured records with header row keys), and the most impactful performance caveat. It could mention explicit return field structure or error cases, but the essential context for correct invocation is present.

  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 100%, so the baseline is 3. The description adds value by explaining how the key parameters interact: 'maxRows/offset/filter/columns are applied AFTER the full sheet is fetched.' This synthesizes the individual parameter descriptions and reveals the ordering semantics, which is not immediately obvious from the schema alone.

  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+resource: 'Read a worksheet as structured records, using the header row as keys.' This distinguishes it from siblings like get_cell_range (raw cells) and describe_sheet (structure) by emphasizing structured row/record output.

  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 clear usage guidance on handling truncation: 'If the result is truncated, narrow it with `filter` or `columns` first, and only page with `offset` as a fallback.' This tells the agent how to use the tool effectively in a common scenario, though it does not explicitly mention when to use this tool over siblings.

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

• describe_sheetA
  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 full burden for behavioral disclosure. It transparently states the tool does not pull the full dataset, returns only headers, row count, and up to 3 sample rows, and is safe to call first. It could add nuance about whether sample rows are the first rows or random, but overall it gives enough context for a read-only inspection 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?

  Two sentences: the first front-loads the purpose and return values; the second gives direct usage guidance. Every word is purposeful, with no fluff or repetition. Highly concise and well-structured.

  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 no output schema and no annotations, the description covers the essential context: what callers receive (headers, row count, sample rows), when to invoke it (first on unfamiliar sheets), and why (to avoid pulling everything). For a simple inspection tool with fully documented parameters, this is 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 description coverage is 100% for all 5 parameters, so the schema already fully documents their meaning. The description adds limited parameter-level detail beyond what the schema provides (e.g., 'headerRow' is self-explanatory). This meets the baseline but does not go further.

  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 a specific verb+resource ('Inspect a sheet') and clearly defines its scope: returns column headers, total row count, and up to 3 sample rows. It also differentiates from sibling tools by emphasizing it's a lightweight inspection ('without pulling its data') and explicitly mentions the targeted use case for get_permission_matrix.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines5/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description provides explicit when-to-use guidance: 'Call this FIRST against an unfamiliar matrix'. It also states why (to build a targeted filter) and contrasts with the alternative 'pulling everything' via get_permission_matrix, effectively giving a when-not scenario. This is clear and actionable.

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

• get_cell_rangeA
  4.6/5.0
  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 adds meaningful behavioral details: 'raw values' (not formatted), and 'the range genuinely bounds what Graph transfers' (performance/scope). However, it doesn't mention potential errors, authentication requirements, or response structure, so it's not a perfect disclosure.

  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 short sentences, each earning its place: purpose, use case, and a distinguishing comparison. No redundancy, and front-loaded with the primary action.

  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 read tool with no output schema, the description does not mention the return format, but the phrase 'raw values' gives a hint. It could be clearer about what the agent gets back, yet it covers selection and invocation well. Slight gap, but overall complete for the core use case.

  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 coverage is 100%, so baseline is 3. The description adds value by providing an explicit range example ('A1:D20') and explaining why the range is important in the context of non-standard layouts, going slightly beyond the schema's parameter 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 uses a specific verb ('Read') and resource ('raw values for an explicit A1 range'), with a concrete example. It clearly distinguishes itself from siblings, especially get_permission_matrix, by stating the range bounds what Graph transfers.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines5/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  It explicitly states when to use the tool: 'when the sheet has a non-standard layout that the header-row model does not fit.' It also names an alternative (get_permission_matrix) and explains the key difference, providing clear selection guidance.

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