Server Quality Checklist

Tool Scores

• guardrails_scan_piiA
  4.5/5.0
  Behavior4/5

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

  Annotations already indicate readOnlyHint=true and idempotentHint=true. Description adds 'deterministic regex engine', 'read-only and safe to retry', and billing info (free offline, costs 1 TNC on hosted). No contradictions.

  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?

  Well-structured: summary sentence, then detailed lists, return format, example, and billing note. No wasted sentences; front-loaded with key info.

  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 simple input (1 required param) and presence of output schema, description covers input semantics, return structure, example, and usage context completely.

  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% with description for 'text' parameter. Description adds context like 'user input, chat messages, documents, log lines' and character limit (50,000), enhancing schema meaning.

  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?

  Description clearly states 'Scan text for personally identifiable information (PII)' and lists 7 specific PII types. Distinguishes from sibling tools (check, injection, secrets) by focusing exclusively on PII.

  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?

  Provides explicit use case: 'audit content before logging, storing, exporting, or sharing' as a GDPR/LGPD check. Mentions read-only and safe to retry. Does not explicitly exclude scenarios or name alternatives, but context is clear.

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

• guardrails_scan_injectionA
  4.6/5.0
  Behavior5/5

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

  Annotations declare readOnlyHint=true, idempotentHint=true. Description confirms 'Deterministic regex engine; read-only and safe to retry' and explains the 10 patterns. No contradiction, and adds behavioral context beyond 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?

  Well-structured: first sentence states purpose, then lists patterns, usage, return format with example, billing note. Front-loaded and efficient, though slightly verbose with the pattern list. Earns its space.

  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?

  Completely describes the tool's purpose, attack patterns, usage, return value structure (with example), and billing. Output schema exists but description covers the return fields adequately. No gaps given the tool's complexity and annotation richness.

  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 only parameter 'text' has a description in the schema covering analysis for injection, language optimization, and character limit. The tool description adds no new param semantics beyond the schema, so baseline 3 applies as schema coverage is 100%.

  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 'Detect prompt-injection and jailbreak attempts in untrusted input' with a specific verb and resource. It lists 10 distinct attack patterns, distinguishing it from siblings like guardrails_scan_pii and guardrails_scan_secrets.

  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 says 'Use it on every piece of untrusted text an agent consumes' and gives examples (user messages, web content, etc.). The billing note adds context for when it costs TNC, implying when alternatives might be considered.

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

• guardrails_scan_secretsA
  4.6/5.0
  Behavior5/5

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

  The description states behavior beyond annotations: 'Deterministic regex engine; read-only, never stores or transmits the scanned content.' This complements the readOnlyHint=true and idempotentHint=true annotations. Additionally, it notes billing costs. No contradictions.

  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?

  Well-structured with a clear front-loaded purpose, list of formats, usage guidance, behavioral notes, return format, and example. Some sentences are slightly long but overall efficient and informative.

  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?

  Covers all necessary aspects: input constraints, detection capability, return structure (including example), usage context, and billing note. The detailed return format description compensates for the absence of an explicit output schema.

  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 schema already has a detailed description for the 'text' parameter (100% coverage). The description adds extra context about suitable input types and the 50,000 character limit, providing more value than the schema alone.

  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 'Scan text or source code for exposed secrets and credentials' and lists 8 specific credential formats. The tool is distinctly different from siblings (guardrails_check, guardrails_scan_injection, guardrails_scan_pii) which focus on other scanning tasks.

  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?

  Provides explicit when-to-use guidance: 'before committing code, pasting logs into tickets, or forwarding text to an external model.' Does not explicitly state when not to use or suggest alternatives, but the context of sibling tools implies this is for secrets only.

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

• guardrails_checkA
  5/5.0
  Behavior5/5

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

  Annotations already declare readOnlyHint=true and idempotentHint=true. The description adds valuable behavioral context: it states the tool uses a deterministic regex engine with no LLM in the loop, ensuring reproducible, side-effect free results. It also lists detection coverage in detail. No contradictions with annotations.

  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 front-loaded. It begins with the primary purpose, then usage guidelines, detection coverage, return format, example, and billing note. Every sentence adds value, and the length is appropriate for the tool's complexity.

  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 tool's complexity and the presence of an output schema, the description comprehensively covers usage, detection scope, return format, example, and even billing. There are no missing elements; it fully informs the agent about how to use 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 coverage is 100%, but the description significantly enhances the parameter 'text' by specifying that it accepts any length up to 50,000 characters and instructs to pass the raw, unsanitized input. This adds critical guidance beyond the schema 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 clearly states the tool's purpose: running a comprehensive pre-flight safety scan combining all three guardrails in one call. It uses a specific verb ('Run') and resource ('pre-flight safety scan'), and distinguishes from sibling tools by noting that focused tools are cheaper for single-category detection.

  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 provides explicit guidance on when to use this tool (before sending untrusted input to an LLM, before logging user content, or before persisting conversation history) and when to prefer alternatives (if only one category needed, use focused tools). This satisfies the requirement for explicit when/when-not/alternatives.

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