Server Quality Checklist

Tool Scores

• treesitter_run_queryA
  4/5.0
  Behavior3/5

  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 explains the output_file behavior (writes to file instead of returning) and mentions the return type depends on query structure. However, it does not mention error handling, side effects, or whether the tool is read-only, leaving gaps.

  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 with Args and Returns sections, each sentence serving a purpose. It is concise yet covers all essential behavioral and parameter details without redundancy, making it 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 complexity and lack of annotations or output schema, the description covers return types, parameter behaviors, and the output_file option adequately. It does not include examples or deeper syntax explanation, but this is not critical for a query execution 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?

  Schema description coverage is 0%, so the description compensates well. It provides meaningful info for each parameter: query format (S-expression), language auto-detection, output_file purpose. This adds value beyond the schema, though file_path is minimally described.

  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: 'Execute a custom Tree-sitter query against a source file.' This is a specific verb+resource combination and distinguishes it from sibling tools by emphasizing 'custom' queries, as opposed to specialized operations like finding usages or getting an AST.

  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 for custom queries not covered by other tools but does not explicitly state when to use this tool vs alternatives. It provides no exclusions or direct comparisons to sibling tools, leaving the usage context somewhat implied.

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

• treesitter_find_variableA
  4.1/5.0
  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 disclosing behavior. It explains the return dictionary and the output_file alternative, but it does not explicitly state that the operation is read-only, how errors are handled (e.g., file not found, no matches), or what Symbol objects contain beyond an optional 'source' field. This leaves notable behavioral gaps.

  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 with Args and Returns sections, opens with a clear one-line purpose, and each parameter and return detail is explained without redundancy. The 'Useful for large outputs' note adds value without bloating the text, and the whole description is appropriately sized for four parameters.

  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 and no annotations, the description covers all parameters and return values, including the output_file alternative. However, it omits details about the structure of Symbol objects, behavior when no matches exist, and error conditions, so it is not fully complete for a tool of this complexity.

  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 parameter explanations in the description are critical. Each argument is given a meaningful description: file_path as 'Path to the source code file,' name as 'Name of the variable to find,' include_source as controlling source inclusion, and output_file as an alternative to returning. This fully compensates for the bare schema and adds significant semantics.

  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 'Search for variable declarations and usages by name,' which specifies a concrete action (search), a resource (variable declarations/usages), and a qualifier (by name). This clearly distinguishes it from sibling tools like treesitter_find_function (functions) and treesitter_find_usage (general usage), making its purpose explicit and 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 does not explicitly state when to choose this tool over alternatives like treesitter_find_usage or treesitter_find_function. Usage is implied from the purpose, and the only additional guidance is the note about output_file being useful for large outputs. No exclusions or alternative tool references are given, so guidance is limited to implied context.

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

• treesitter_find_functionA
  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 full burden. It discloses the output structure (query and matches), the include_source behavior, and the output_file side effect with rationale ('prevent context overload'). This goes beyond a simple 'search' statement, though it doesn't cover error cases or read-only guarantees. The behavioral details are valuable and missing from schema/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?

  The description is structured with Args and Returns sections and is front-loaded with a clear action. It is somewhat longer than necessary but each sentence provides useful context, such as the rationale for output_file. No filler or repetition.

  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 4 params, no output schema, and read-only intent, the description covers all key aspects: purpose, parameters, return format, conditional behavior, and alternate output method. It lacks explicit comparison to siblings, but that is a usage-guideline gap. Overall, it is complete enough for an agent to invoke the tool correctly.

  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 has only titles and defaults (coverage 0%), so the description is the sole source of parameter meaning. It explains file_path, name, include_source with a clear condition, and output_file including its purpose and benefit. This fully compensates for the lack of schema 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 opens with 'Search for a specific function definition by name,' which clearly states the tool's precise action and target resource. It distinguishes from sibling tools like treesitter_find_variable or treesitter_find_usage by specifically limiting to function definitions.

  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 when to use this tool (when you need a function definition by name) but gives no explicit alternatives or exclusions. It doesn't mention 'use treesitter_find_variable for variable lookup' or 'avoid this for AST queries.' Usage context is clear but not explicitly compared to siblings.

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

• treesitter_get_source_for_rangeA
  4.2/5.0
  Behavior4/5

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

  With no annotations, the description effectively discloses behavior by detailing both return modes (inline source text or writing to an output file) and the reason for the output_file mode. It also provides the 0-based indexing context for coordinates. However, it does not mention potential errors or edge cases like out-of-bounds ranges, which would be useful but not critical for this read-only operation.

  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 well-structured, starting with a one-sentence purpose, followed by a clear Args list and Returns specification. It is compact without unnecessary fluff. The Args section repeats parameter names from the schema, but it's justified because it adds crucial detail about row/column conventions and output_file semantics.

  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 lack of annotations and output schema, the description does a strong job of covering all parameters, both return modes, and the rationale for the output_file option. It stops short of defining range inclusivity (e.g., whether end_row/end_column are exclusive), which could lead to off-by-one errors. Overall, it is sufficiently complete for an experienced user.

  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 schema parameters are minimally described (e.g., 'End Row'), but the description attaches meaning to every parameter in the Args section, including their 0-based nature and the output_file behavior. This fully compensates for the 0% schema description coverage, making the parameters self-explanatory.

  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: 'Extract the source code text for a given line/column range.' This specific verb and resource distinguish it from sibling tools like treesitter_get_node_for_range, which extracts AST nodes, and treesitter_run_query, which runs queries. The scope is 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 usage when raw source text for a range is needed, but it does not explicitly mention when to use this tool over alternatives like get_node_for_range or cursor_walk. It does provide a specific guideline for the output_file parameter (useful for large outputs to prevent context overload), but lacks broader contextual guidance or exclusions.

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

• treesitter_cursor_walkA
  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 transparency burden. It discloses the output_file side effect ('writes result to this file instead of returning') and clearly describes the return shape or alternative written status. It does not mention error cases or file overwriting behavior, but the main behavioral traits are transparent.

  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 with Args and Returns sections, uses concise single-line explanations for each parameter, and includes only the necessary extra context about output_file. There is no fluff or redundancy; every sentence earns its place.

  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 no annotations and no output schema, the description provides a solid foundation: purpose, all parameter semantics, and return shape. It is enough to invoke the tool correctly, but the return dictionary is only vaguely described as 'focus, ancestors, siblings, and children' without field types or structure, leaving some ambiguity for a complex AST tool.

  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 schema has no parameter descriptions (0% coverage), but the description's Args section explains every parameter: file_path is a path, row/column are 0-based, max_depth controls AST depth, and output_file writes to a file instead of returning. This fully compensates for the schema gaps and adds useful context such as the rationale for output_file.

  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 and resource: 'Return a cursor-style view (focus node + context) at a point.' It also lists the returned components (focus, ancestors, siblings, children), which clearly differentiates it from sibling tools like treesitter_get_node_at_point that likely return only a single node.

  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 through the 'cursor-style view' phrasing and provides a concrete guideline for the output_file parameter: 'Useful for large outputs to prevent context overload.' However, it does not explicitly state when to prefer this tool over alternatives or mention any exclusions, so it stops short of clear sibling differentiation.

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

• treesitter_find_usageA
  4.3/5.0
  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 clearly discloses the file-writing side effect of output_file and explains the two possible return shapes. It does not mention error cases or the internal structure of Symbol objects, but it gives a solid, honest behavioral overview.

  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 and well-structured with clear Args and Returns sections. Every sentence earns its place—no fluff, and the most important information is front-loaded in the first 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?

  Given there is no output schema, the description does a good job of explaining the return format and the output_file alternative. It is slightly incomplete in that it does not describe the fields of Symbol objects or behavior on no matches, but it is sufficient for an agent to invoke the tool correctly.

  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%, but the description fully compensates by documenting all four parameters with meaningful semantics: name, file_path, language override, and the output_file behavior. This exceeds the baseline and makes the schema usable.

  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 and resource: 'Find all usages/references of a symbol (identifier) in a source file.' This clearly distinguishes it from sibling tools like treesitter_find_function and treesitter_find_variable, which focus on definitions rather than usages.

  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 provides practical guidance for the output_file parameter ('Useful for large outputs to prevent context overload') and explains the language auto-detection behavior. However, it does not explicitly state when to choose this tool over nearby alternatives such as treesitter_run_query or treesitter_find_variable, so the when-not guidance is missing.

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

• treesitter_get_dependenciesA
  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 of behavioral disclosure. It explains the return format for different languages (Python, C/C++) and the behavior of the output_file parameter (writes to file instead of returning). It also notes a key benefit (avoiding context overload). It does not mention error handling or unsupported languages, but the provided details are substantial.

  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 with a clear opening sentence, a brief args section, and a return section. It is concise (about 100 words) and every sentence provides useful information without fluff. The front-loading is effective.

  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 (2 params, no output schema, no annotations), the description covers the essentials: what it does, how parameters work, and what the return value looks like. It could mention supported languages beyond Python and C/C++, but the core functionality is clearly documented.

  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 fully compensate. It does: file_path is described as 'Path to the source code file' and output_file is explained as 'If provided, writes result to this file instead of returning. Useful for large outputs to prevent context overload.' This adds clear meaning beyond the bare schema types.

  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+resource: 'Extract all dependencies (imports/includes) from a source file.' This distinctly sets it apart from sibling tools like treesitter_get_ast or treesitter_run_query, which serve 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 Guidelines3/5

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

  The description provides some usage context (e.g., output_file for large outputs to prevent context overload) but does not explicitly mention when to use this tool versus alternatives or when not to use it. The usage is implied by the tool's purpose, but no exclusions or alternative recommendations are provided.

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

• treesitter_get_node_for_rangeA
  4.4/5.0
  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 explains max_depth semantics, the output_file side effect (writes to file instead of returning), and the return format. It does not discuss error cases, but for a read-only operation this is sufficient.

  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 with a one-line summary, an Args list, and a Returns section. It is concise, front-loaded, and every sentence adds value 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?

  Given the absence of output schema and annotations, the description is complete: it covers the tool's purpose, all parameters, and return values including the alternative file-write mode. The only missing elements are edge-case error handling, which is not critical for typical use.

  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 has no descriptions for parameters, so the description's Args section is essential. It provides 0-based row/column details, max_depth meaning, and output_file behavior, covering all 7 parameters with actionable context beyond simple 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 'Return the smallest AST node covering a point range,' using a specific verb and resource. It distinguishes itself from siblings like treesitter_get_node_at_point by specifying range coverage and 'smallest' node.

  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 node spanning a range is needed, and the output_file option provides context for large outputs. However, it does not explicitly mention alternative tools or when not to use this tool, relying on inferred applicability.

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

• treesitter_get_call_graphA
  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 full burden of behavioral disclosure. It thoroughly details the return structure and the alternate file-writing behavior, including the status dict. This is strong transparency for a read-only analysis tool, though it does not cover potential errors or edge cases.

  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 front-loaded with a clear one-sentence summary, followed by compact Args and Returns sections. It is concise, well-structured, and every sentence provides value without 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?

  The description covers the core functionality, parameter effects, return format, and the alternative output mode, which is sufficient given the tool's simplicity and lack of an output schema. Minor gaps like error handling or language support are not critical for basic usage.

  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 schema has no parameter descriptions (0% coverage), so the description's explanations of file_path and output_file add essential meaning. It goes beyond the schema by explaining the default behavior (returns graph) and the conditional behavior (writes to file and returns status).

  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 it generates a call graph showing function calls and their relationships, using a specific verb and resource. This distinguishes it from sibling tools like treesitter_get_dependencies or treesitter_get_ast.

  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 context on when to use the tool (to obtain a call graph) and gives a practical tip about using output_file for large outputs to prevent context overload. However, it does not explicitly mention alternative tools or when not to use it.

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

• treesitter_get_node_at_pointA
  4.5/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the full burden. It explains the output_file behavior and its rationale (preventing context overload), the max_depth semantics, and the return format. It does not cover error cases or node selection logic when multiple nodes cover a point, but overall it is transparent.

  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 with a one-sentence purpose, a concise Args list, and a Returns section. Every line adds value, and the output_file note is succinctly integrated. 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?

  The description covers the core functionality, all parameters, and the return format including the output_file alternative. Minor missing details include how overlapping nodes are resolved and error handling, but these are not critical for a read-only query tool.

  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 description provides a clear explanation for each of the five parameters, including row/column being 0-based and the meaning of max_depth. This fully compensates for the input schema's lack of descriptions (0% coverage).

  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 'Return the AST node covering a specific point (row, column).' It uses a specific verb and resource, and the point-based scope distinguishes it from siblings like treesitter_get_node_for_range and treesitter_get_ast.

  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 context for when to use the tool (querying a single point) but does not explicitly mention alternatives or exclusions. The context is sufficient for an agent to differentiate from range-based or whole-tree tools.

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

• treesitter_get_astA
  4.6/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the full burden. It clearly explains the return format (dictionary with type, start_point, end_point, children) and the alternative behavior when output_file is set (writes to file and returns a status dictionary). It also hints at potential issues like serialization errors. However, it does not explicitly state whether the tool is read-only or discuss side effects, though it is implied by 'Extract'.

  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-organized with a clear opening sentence, an Args section, and a Returns section. Every sentence provides value: the main purpose, parameter details, and return structure. It is concise given the amount of information needed and front-loads the primary action.

  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 tool with 3 parameters and no output schema, the description covers all necessary aspects: what the tool does, each parameter's role, return values, and edge-case behavior (output_file). It even notes practical limitations for large files. There are no significant gaps, making it highly complete for the tool's complexity.

  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%, but the description compensates fully by explaining each parameter: file_path is 'Path to the source code file', max_depth is 'Maximum depth of the AST to return. -1 for no limit' with practical advice, and output_file is 'If provided, writes result to this file instead of returning' with rationale. This adds substantial meaning beyond the bare 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 uses a specific verb and resource: 'Extract the complete Abstract Syntax Tree (AST) from a source file.' This clearly states the tool's function and distinguishes it from siblings like treesitter_get_node_for_range (which targets specific nodes) and treesitter_get_source_for_range (which retrieves source text).

  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 for parameters, e.g., 'max_depth' is 'Useful for large files to avoid serialization errors' and 'output_file' is 'Useful for large outputs to prevent context overload.' It implies when to use these options, though it does not explicitly compare to alternative sibling tools or state when not to use the tool.

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

• treesitter_get_supported_languagesA
  4.6/5.0
  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. It clearly explains two possible behaviors: returning a list of languages, or writing to a file if output_file is set, including the exact return structure in both cases. It also notes the rationale for output_file ('prevent context overload'), which adds useful behavioral 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?

  The description is well-structured: a one-line summary followed by Args and Returns sections. Despite being longer than a single-sentence description, every sentence earns its place, and the most important information (purpose and return) is front-loaded.

  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 tool with one optional parameter and no output schema, the description is complete. It covers purpose, parameter semantics, and both possible return shapes. No important information is missing.

  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 coverage is 0%, but the description fully compensates. It explains the output_file parameter's meaning (writes to file instead of returning), its use case (large outputs), and the resulting return value. This adds far more context than the bare schema (a string/null parameter with no 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 opens with a clear, specific verb: 'Get a list of programming languages supported by the analyzer.' It names the resource (supported languages) and uniquely distinguishes this tool from siblings that focus on AST traversal, queries, and analysis.

  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 guidance is only implied. The tool's purpose is obvious from the description, but it never explicitly states when to use this tool versus alternatives or mentions any context or prerequisites. The output_file parameter description gives a minor usage hint for large outputs, but no overall usage guidelines.

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

• treesitter_analyze_fileA
  5/5.0
  Behavior5/5

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

  With no annotations provided, the description carries full behavioral burden. It discloses that the function does not return the full AST due to serialization issues, can write results to a file, and returns a structured dictionary with specific fields. It also lists supported file extensions, providing valuable context beyond the bare schema.

  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 and concise: a one-sentence purpose, followed by clear Args/Returns sections and a note. Every sentence contributes useful information without redundancy or fluff.

  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, the description details the return dictionary structure. It also covers limitations, error handling ('errors' field), and alternative tool usage. Given the tool's simplicity (2 params, 1 required), the description is fully sufficient for an agent to select and invoke it correctly.

  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 fully compensates: file_path is described as 'Path to the source code file to analyze (supports .py, .c, .cpp, .h, .hpp)' and output_file is explained as 'If provided, writes result to this file instead of returning. Useful for large outputs to prevent context overload.' This adds significant meaning beyond the property names.

  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 purpose: 'Analyze a source code file and extract symbols (functions, classes, etc.)'. It specifies the verb 'extract' and the resource 'source code file', and distinguishes itself from siblings by noting it returns symbols rather than the full AST.

  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?

  Explicitly provides guidance on when to use an alternative: 'Use treesitter_get_ast() if you need the complete AST.' Also explains when to use the output_file parameter ('Useful for large outputs to prevent context overload'), giving clear context for choosing options.

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