Server Quality Checklist

Tool Scores

• delete_paragraphA
  3.6/5.0
  Behavior3/5

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

  The description indicates the deletion uses 'revision mode,' suggesting a non-destructive tracked change. However, it does not detail what happens to the paragraph content (e.g., moved to revision history) or any required permissions. With no annotations, more behavioral context would be beneficial.

  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 a single concise sentence with no extraneous text. It is front-loaded with the action and includes a cross-reference. While effective, it could be slightly more structured without adding length.

  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?

  For a delete operation with revision mode and three parameters, the description provides minimal but essential context. It references read_document for index but does not cover return values (though output schema exists) or reversibility. The description is adequate but not thorough.

  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?

  With 0% schema description coverage, the description must compensate. It explains the 'index' parameter via reference to read_document, but does not elaborate on 'path' or 'author' (default 'AI 律师助手'). The description adds some value for index but leaves other parameters unexplained.

  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 (delete paragraph) and the specific resource (paragraph at index 0-based), referencing read_document for index understanding. It distinguishes from siblings like insert_paragraph and replace_text by highlighting revision mode.

  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 deleting paragraphs by index but provides no explicit guidance on when to use this vs alternatives (e.g., replace_text or insert_paragraph). No exclusions or conditions are mentioned.

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

• list_revisionsA
  3.9/5.0
  Behavior3/5

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

  No annotations provided, so description carries full burden. It states the tool lists revisions (read operation) but does not explicitly declare it as read-only or safe. It adds a behavioral detail about including manual revisions, but lacks notes on prerequisites or side effects.

  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 core purpose, and each sentence adds value. No unnecessary words. It is 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?

  The tool has one simple parameter and an output schema (not shown). The description explains the purpose and use cases adequately. It lacks details about path validation or document existence requirements, but this is a minor gap given the simplicity.

  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%. The only parameter is 'path', and the description does not explain its meaning or expected format. The parameter semantics rely entirely on the schema name, which is insufficient for effective use.

  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 lists all existing revisions (including manual ones) and returns JSON. It provides specific use cases (post-editing self-check, reporting revisions). The verb 'list' and resource 'revisions' are clear, and it distinguishes from sibling tools which are editing 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 gives explicit usage context: after editing to self-check or to report revisions. It does not explicitly state when not to use it or list alternatives, but the context of sibling tools (all modification actions) makes it clear this is for reading revision history.

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

• replace_textA
  4.1/5.0
  Behavior4/5

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

  With no annotations provided, the description bears full responsibility for behavioral disclosure. It transparently explains the Track Changes behavior, the condition that old_text must appear only once for replacement, and that empty new_text means deletion. It lacks details on permissions or response format, but the core behavioral traits are well communicated.

  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 concise, using a single paragraph with line breaks for clarity. It front-loads the key purpose and behavioral details. Every sentence adds value, though some parameter descriptions could be more structured. It achieves good readability without excessive verbosity.

  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 has 5 parameters and an output schema (not shown). The description covers the main behavioral aspects and parameter usage for the most critical parameters. It does not address the return value, but the presence of an output schema mitigates this. The description is mostly complete for a text replacement tool, though missing details on path and author could be improved.

  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 input schema has 5 parameters with 0% schema description coverage. The description adds meaning to old_text (must appear once), new_text (empty means deletion), and replace_all (boolean to replace all). However, path and author parameters are not explained; path's role as document path is implicit, and author's default value is not described. The description partially compensates for the schema gaps but not fully.

  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 replaces text using Track Changes mode, with specific verb '替换' (replace) and resource '文档中的文本' (text in document). It distinguishes from siblings like delete_paragraph and insert_paragraph, which operate on different structural units.

  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: it replaces text with revisions, noting that modifications are not direct but become Word revisions. It specifies conditions for replacement (single occurrence) and options (replace_all=True). However, it does not explicitly state when not to use the tool or suggest alternatives beyond the implicit context.

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

• insert_paragraphA
  4.2/5.0
  Behavior4/5

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

  The description explicitly states that insertion uses revision mode, which is a key behavioral trait. With no annotations provided, this adds important context. It also explains the index counting method, but does not cover all behavioral aspects like whether styles must exist or what the output contains.

  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 conveying all essential information without any redundant phrases. It is well-structured and front-loads the core 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?

  Given the presence of an output schema and 5 parameters, the description provides sufficient context for the key parameters and insertion behavior. It references read_document for index counting, aiding understanding. However, missing explanation for path and author slightly reduces completeness.

  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 adds meaning for after_index (counting from 0, see read_document) and style (optional, existing style names). However, it does not explain path, text, or author parameters, leaving gaps for 3 out of 5 parameters.

  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 inserts a new paragraph after a specific index using revision mode. It distinguishes from siblings like delete_paragraph and replace_text by specifying the action and context.

  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 implies usage by mentioning the after_index parameter and reference to read_document for index counting, and notes style is optional with existing names. However, it does not explicitly state when not to use this tool or provide alternatives like replace_text.

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

• read_documentA
  4.5/5.0
  Behavior4/5

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

  No annotations provided, so description carries full burden. It discloses the output format (JSON array with index, style, text) and how text is computed (after accepting all revisions). It does not mention permissions or side effects, but for a read tool 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?

  Three sentences, each serves a purpose: first states action, second gives constraint, third describes output and usage. No unnecessary 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?

  Given the presence of an output schema (not shown), the description adequately explains the return structure. It also ties to sibling tools by noting the prerequisite relationship. For a read tool with one parameter, this is 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?

  Schema coverage is 0%, so description must compensate. It adds that 'path must be absolute path', which is crucial beyond the type 'string'. Also it implies that the path points to a .docx 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 clearly states 'Read all paragraphs of a Word document (.docx)', specifying the verb (read) and resource (document paragraphs). It distinguishes from sibling editing tools by saying 'must read before editing', establishing it as a prerequisite.

  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 'Must read the document before editing', providing clear usage context. It does not explicitly state when not to use it, but the implication that it's for reading before editing is strong.

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