Server Quality Checklist

Tool Scores

• fix_textA
  3.8/5.0
  Behavior4/5

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

  With no annotations, the description carries the transparency burden and does so well: it states the default safe rule scope, what is explicitly left untouched (code blocks, inline code, URLs), that it will report changes, and that some items need manual confirmation. This is strong for a pure text transformation tool.

  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 compact and structurally clear, starting with purpose and then behavior, followed by parameter explanations. Every sentence carries information; no fluff. Slight density from the in-description argument block is the only reason it doesn't reach 5.

  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 a pure text-processing tool with 3 simple parameters and an output schema, the transparency is mostly complete. It explains default behavior, rules selection, and quote style. It fails to point at sibling tools like list_rules for available rule names, but that is not required for a 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?

  Schema description coverage is 0%, so the description must fully compensate. It does: text is explained, rules details comma-separated exclusion and forced inclusion with an example, and quote_style enumerates all three modes with symbols. No meaningful parameter definition is left to inference.

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

  Purpose4/5

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

  The description states a specific action (自动修复) and resource (中文文案的排版问题) and says it returns the full fixed text. This clearly marks the tool as a fixer rather than a checker/counter, but it doesn't name sibling tools, so differentiation is implicit rather than explicit.

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

  Usage Guidelines2/5

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

  The description gives no guidance on when to use this tool instead of its siblings (check_text, count_text, list_rules). It provides parameter-level usage details, but not when-to-use/exclusion guidance, which is the key here.

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

• count_textA
  3.9/5.0
  Behavior3/5

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

  With no annotations, the description carries the disclosure burden. It states that per-platform limit status will be returned together with the stats, which is useful, but it does not mention side effects, permissions, error behavior, or the exact output structure. For a read-only counting tool this is adequate but not 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 main functionality is front-loaded in the first sentence, followed by a brief note on the included platforms and a compact Args section. Every sentence adds information; there is 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?

  The description provides enough for correct invocation: required text, optional platform filtering, and the general nature of the returned data. The output schema covers the return shape. The only minor gap is that the full list of valid platform codes is not enumerated, only examples.

  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 compensates fully: 'text' is defined as the text to count, and 'platforms' is explained as an optional comma-separated filter with an example ('xhs_title,mp_digest') and a clear default ('empty means all'). This exceeds what the schema alone provides.

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

  Purpose4/5

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

  The description clearly states the tool's function: counting characters, paragraphs, sentences, reading time, and checking platform-specific length limits. It is distinct from fix_text and list_rules, and the counting focus differentiates it from check_text, though no sibling is explicitly named.

  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 intended use is implied by the purpose: call this when a text's statistics or platform-limit status is needed. There is no explicit guidance on when not to use it or which sibling tool to prefer, leaving the comparison to inference.

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

• list_rulesA
  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 full burden. '列出全部' explicitly states the tool lists all rules (read-only, no side effects), and the field list (id, level, auto-fixable, description) tells the agent what to expect in the result. This sufficiently covers behavior for a simple zero-parameter list 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 short sentences with no filler. The first sentence states the core function and output fields; the second provides concrete usage guidance. Every word 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?

  For a zero-parameter tool with an output schema, the description is nearly complete: it states scope, returned fields, and a concrete use case. It could have added a note about behavior (e.g., always returns all rules rather than paginated), but given the simple read-only nature and existing output schema, it is sufficiently 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 has 0 parameters, so the baseline is 4. The description adds extra context that this tool serves to explain the 'rules' parameter used elsewhere, which is semantically useful beyond the empty 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 ('列出'/'list') and resource ('全部校对规则'/'all proofreading rules') and enumerates the returned fields (id, level, auto-fixable status, description). This clearly distinguishes it from siblings like check_text, fix_text, and count_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 second sentence gives explicit conditions for use: when you need to know what values the 'rules' parameter accepts or understand a rule's boundaries. It does not name sibling tools or exclusions, but the context is clear enough for an agent to route to this tool versus the siblings.

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

• check_textA
  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 and does it well: it explicitly states the operation is read-only, will not modify anything, and automatically skips code blocks, inline code, URLs, emails, HTML tags, and formulas. It also reveals default rule behavior and the default issue limit.

  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 the core purpose and read-only guarantee, then presents parameters as a clean Args block with concrete examples. Every sentence adds useful information, and the formatting makes scanning easy.

  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 4-parameter tool with no annotations, the description covers required and optional parameters, defaults, allowed severity values, rule syntax, and ignored content. Since an output schema exists, there is no need to explain return values; what an agent needs to invoke the tool correctly is present.

  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%, and the description compensates thoroughly. For each parameter it adds meaning absent from the schema: text accepts Markdown and defines skipped elements; rules documents comma-separated inclusion, '-' prefix exclusion, and the default set; severity enumerates valid values; limit states default 30.

  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 states a specific verb ('检查') and resource ('中文文本'), and enumerates the exact scope: 排版、标点、常见错别字、专有名词大小写. It also notes the operation is read-only, which distinguishes it from sibling fix_text without requiring schema inspection.

  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 establishes a clear context—this is a read-only checker that does not modify text—so an agent can infer it is for analysis rather than fixing. However, it never explicitly names or contrasts the sibling tools (fix_text, count_text, list_rules) or states conditions for choosing one over another; guidance remains implied.

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