Server Quality Checklist

Tool Scores

• unmask_textA
  4.2/5.0
  Behavior3/5

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

  With no annotations, the description carries full burden. It explains token replacement and session requirement, but does not specify return value, error conditions (e.g., invalid session), or idempotency. Adequate but not comprehensive.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

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

  Two concise sentences with clear purpose first, then additional details. 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?

  Sufficient for a simple restore tool with two parameters. Output is implied (restored text) but not explicitly stated. No mention of failure modes, but given low complexity, this is acceptable.

  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 covers both parameters (100% coverage). Description adds value by specifying token format like [PESEL:1] and that session_id must come from mask_text. Adds context beyond 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 clearly states it restores original sensitive values in text that was previously masked by mask_text, using specific verb 'restore' and resource 'text'. It distinguishes from sibling mask_text by describing the reverse operation.

  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?

  Explicitly says to use after mask_text and that session_id must come from mask_text. This gives clear context for when to use. However, no explicit when-not or alternatives beyond the sibling.

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

• mask_textA
  4.3/5.0
  Behavior5/5

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

  With no annotations provided, the description carries full responsibility for behavioral disclosure. It is exceptionally transparent: it details the token format, the default locale packs and the disabled_locales/locale_warning behavior when the server is constrained, the NER loading wait mechanism (wait_for_ner), and the session_id semantics. This goes well beyond a typical description and leaves no ambiguity about side effects or limitations.

  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 and front-loaded with the core purpose. Each paragraph contributes information: entities, locale behavior, return values, and restoration hint. It is longer than a minimal description but every sentence earns its place given the tool's complexity. No redundancy or fluff.

  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 that there is no output schema, the description must explain return values, and it does: masked text plus session_id, plus the active_locales/disabled_locales fields. It also explains the custom_literals behavior and the NER wait option. The description covers all necessary invocation details for an agent to call this tool correctly, though it doesn't mention error conditions or pagination—acceptable for this complexity.

  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%, with each parameter (text, session_id, wait_for_ner, custom_literals) already documented meaningfully in the schema. The description adds only marginal value—e.g., connecting session_id to restoration and explaining the effect of wait_for_ner—but does not significantly deepen understanding beyond the schema. Baseline is 3, and the description does not elevate it.

  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: 'Pseudonymize sensitive entities in text before sending to a cloud LLM.' It specifies the types of entities (national IDs, tax IDs, phone numbers, etc.) and the methods (regex and local NER). It also distinguishes itself from the sibling tool unmask_text by explaining the restoration role, making it unambiguous what this tool does and how it differs.

  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: 'before sending to a cloud LLM' and explicitly notes that unmask_text is used to restore original values via session_id. While it does not enumerate exclusions (e.g., when not to use), the primary use case is well-defined and the alternative is named. This is sufficient guidance for an agent to select it appropriately.

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