Server Quality Checklist

Tool Scores

• humanizer_reportA
  3.9/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context beyond annotations, particularly the note that 'added' does not affect the exit code and that out-of-scope inputs receive an out-of-scope status.

  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 dense paragraph that front-loads the tool's output contents before moving to restrictions. Every clause adds useful information; the sentence is somewhat long and run-on, but it remains readable and information-dense.

  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 rich annotations, full schema coverage, and presence of an output schema, the description is sufficiently complete. It covers scope limits, what the report contains, and an important exit-code nuance. It does not elaborate on all report fields, but the output schema likely handles that.

  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%, so both parameters are documented structurally. The tool description does not add parameter-specific details beyond what the schema provides, and the two parameter descriptions are identical, but the parameter names text_before/text_after make their roles reasonably clear in context.

  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 that the tool produces a machine-readable edit report and enumerates its components (keep/add/delete tokens, adapted SARI, edit classes, fact check, MTLD). It is distinguishable from sibling tools like humanizer_polish and humanizer_detect by the report-focused framing, though it does not explicitly name any sibling as a contrast.

  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 includes an explicit 'Когда не использовать' section listing exclusions: non-Russian texts and source code, and use cases where authorship/quality/style verdicts are needed. It does not name specific alternative tools, but the negative guidance is concrete enough for an agent to avoid misuse.

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

• humanizer_scanA
  3.9/5.0
  Behavior4/5

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

  Annotations already mark the tool as read-only, idempotent, and non-destructive. The description adds meaningful behavioral context: it is a category counter, it calibrates editing volume, and it deliberately refrains from authorship judgments. This goes beyond the annotations without contradicting them.

  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 front-loaded with the core purpose, followed by an important exclusion. It has no fluff, but the two clauses run together without clear separation, slightly reducing structural clarity.

  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 a full input schema, an output schema, and strong annotations, the description supplies the key missing contextual information: what the tool measures, how it is meant to be used, and what it must not be used for. It is sufficient for correct invocation, though it could explicitly mention alternatives.

  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%, so the schema already explains both parameters and the genre enum's effective values. The description does not add parameter-level detail, but the baseline of 3 applies because the schema carries the full semantic burden.

  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 clear function: detecting 'soft signs' of machine writing and providing a category counter that calibrates the volume of editing. It also distinguishes itself from verdict-style tools by explicitly denying authorship verdicts, though it does not name sibling tools or use an explicit verb like 'scan'.

  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 a clear negative usage boundary: it does not provide an authorship verdict in any combination of features. This tells the agent when not to rely on it, but it does not name alternatives or explicitly state when to prefer sibling tools, so it falls short of full guidance.

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

• humanizer_factsA
  4.1/5.0
  Behavior5/5

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

  The description discloses behavioral details beyond the annotations: it outputs lost/added/changed with positions, notes that 'added' does not affect the exit code, and states it does not provide authorship/quality/style verdicts. These details meaningfully extend the readOnly/idempotent annotations and help an agent set expectations.

  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 dense and front-loaded with the core purpose, followed by exclusions and behavioral notes. It is somewhat run-on but every clause adds relevant information; no filler or repetition.

  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 output schema exists and the two parameters are fully documented, the description covers the remaining context: scope, exclusions, fact categories, output shape, and exit-code behavior. An agent has enough information to decide when to use this tool and what result to expect.

  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%: both text_before and text_after have explanatory descriptions in the schema. The tool description itself does not add parameter-level meaning beyond what is already in the schema, so the baseline score of 3 is appropriate.

  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 opens with a specific verb+resource ('сверка фактов двух версий текста') and enumerates fact categories (numbers, dates, URLs, e-mail, etc.). This makes the tool's function quite clear, but it does not explicitly differentiate itself from sibling tools by name, relying instead on the distinct fact-checking domain.

  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 'Когда не использовать' section explicitly lists exclusions: non-Russian texts, source code, and authorship/quality/style verdicts. This gives clear when-not-to-use guidance, though it does not name alternative sibling tools, so the when-to-use guidance is only implied rather than contrasted with alternatives.

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

• humanizer_polishA
  4.3/5.0
  Behavior5/5

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

  Beyond the annotations, the description discloses important behaviors: default mode strips Markdown markers like ## and **, normalizes line endings to LF, and does not touch lexical content. The Markdown-stripping warning is material for safe use. This is not an annotation contradiction because the destructive warning concerns transformed content, not an external side effect.

  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 front-loads the core purpose before the exclusions, with no filler. It loses one point for being a dense single run-on sentence with many semicolon-separated clauses, which is slightly harder to scan than a short structured list.

  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 rich input schema, output schema, annotations, and the explicit usage exclusions, an agent has enough information to select and invoke the tool correctly. The only minor gap is that the lexical/sense-editing exclusion does not point to which sibling tool should be used instead.

  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%, and the input schema already documents the mode enum and text scope in rich detail. The top-level description adds some behavioral context but repeats much of what the schema already explains, so it stays at the baseline for fully documented schemas.

  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 opens with the specific operation 'типографическая нормализация' and enumerates concrete targets: dashes, quotes, ellipsis, invisible characters, markup markers, and LF line endings. This clearly identifies what the tool does, but it does not explicitly name or contrast sibling tools, so it stops short of full sibling differentiation.

  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 has an explicit 'Когда не использовать' section. It warns not to run on Markdown/markup with the default mode, names the correct modes to use instead (--preserve-markup and --typographic), and states that the tool does not perform lexical or semantic editing. This provides strong when/when-not/alternative guidance.

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

• humanizer_markersA
  4.5/5.0
  Behavior5/5

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

  The description goes well beyond the annotations by disclosing the risk-classification behavior for removal (safe automatic, ambiguous opt-in, dangerous never) and the interpretive limitation that missing markers do not prove human authorship. It also clarifies scope boundaries for container files, adding real 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.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is dense and information-rich with no filler, front-loading the core purpose and then giving exclusions. It is somewhat run-on and semicolon-heavy, which slightly harms readability, but every part 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?

  With output schema, annotations, and schema-level parameter descriptions present, the description covers purpose, limitations, alternatives, and risk behavior well. The main gap is the unresolved relationship between the described --remove behavior and the actual structured input schema.

  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 coverage is 100%, so the baseline is 3; the schema already documents text and marker_class well. The description adds useful domain context about classes A and B, but it also mentions a --remove flag that is not present in the input schema, which may confuse an agent about how to invoke that behavior.

  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 finds and shows copy-paste/chat-interface artifacts via 40 markers of classes A and B, and can remove invisible text-layer marks with --remove. It also distinguishes itself by explicitly saying it is not a generation detector, which separates it from humanizer_detect and related siblings.

  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 includes an explicit 'Когда не использовать' section: it is not a generation detector, absence of markers does not prove human authorship, and container files should go to scripts/filemarks instead. This gives concrete when-not-to-use conditions and names alternatives.

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

• humanizer_detectA
  4.6/5.0
  Behavior5/5

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

  Beyond the annotations (readOnly, idempotent, non-destructive), the description reveals that the tool only looks at connective-word frequency, that it is not validated for essays/fiction, and that it never returns an authorship verdict. These are meaningful behavioral constraints an agent needs before calling.

  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 a compact single sentence in Russian with a leading definition followed by exclusions. Every clause carries information, and the structure front-loads the purpose before restrictions, making it scannable.

  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?

  With a complete input schema, a present output schema, and annotations covering safety, the description fills the remaining gaps: applicability domain, invalid genres, and the no-authorship-verdict limit. Nothing needed to decide whether to call the tool is missing.

  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 parameters are already documented. The description adds value by mapping the effective genre domain ('чистая проза, инструкции') to the genre parameter, helping an agent choose appropriate values, though it does not describe the text parameter beyond what the schema already says.

  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 the core signal ('частота связок') and its purpose ('признак машинного текста') within a restricted domain ('чистая проза, инструкции'), making the tool's function clear. However, it never names sibling tools, so an agent must infer differentiation from the domain restrictions rather than an explicit comparison.

  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 gives an explicit positive domain ('чистая проза, инструкции') and a detailed 'Когда не использовать' list covering essays, fiction, and web text with artifacts, plus a hard boundary that no authorship verdict is ever produced. This is strong when/when-not guidance, even without naming alternative tools.

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