Server Quality Checklist

Tool Scores

• get_guardrail_statsA
  4.2/5.0
  Behavior3/5

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

  No annotations provided, so description carries full burden. It discloses return structure but does not mention performance, data freshness, or required permissions. Lacks depth expected for an unannotated 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?

  Concise two-sentence description with clear Returns section. Every sentence provides value, no redundancy.

  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?

  No output schema, so description helpfully lists return fields. Covers essential information for a stats endpoint, though missing details like time range or data freshness.

  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?

  No parameters exist, so description cannot add beyond schema coverage of 100%. Baseline score of 4 applies as no additional parameter info is needed.

  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?

  Clearly states it gets aggregate statistics across all scans, specifying breakdowns by risk level, scan type, and recommendation. Differentiates from siblings like get_audit_trail (detailed logs) and scan_input/scan_output (individual scans).

  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 'Use this for a dashboard-style overview', indicating when to use it. Context with sibling tools implies it is for aggregate summaries rather than individual records, but no explicit when-not-to-use.

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

• get_audit_trailA
  4.5/5.0
  Behavior4/5

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

  Without annotations, the description reveals important behavioral traits: it retrieves recent entries (ordering), does not return full scanned text (privacy limitation), and lists return fields. However, it does not explicitly state if the operation is read-only or has side effects, though it is implied to be read-only.

  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 with clear Args and Returns sections, and every sentence contributes value. It is moderately concise, though could be slightly more compact without losing clarity.

  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 simplicity (2 optional params, list retrieval), the description is complete: it covers purpose, parameter usage, return fields, and a privacy note. An output schema exists (per context signals), so the description does not need to duplicate structure.

  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?

  Despite 0% schema description coverage, the description thoroughly explains both parameters: 'limit' (max entries, most recent first) and 'risk_level' (optional filter with allowed values 'low', 'medium', 'high'). This adds significant meaning beyond the schema's type and default.

  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 'Retrieve recent entries from the guardrail audit log', which specifies the verb and resource clearly. It distinguishes from siblings like 'get_guardrail_stats' (aggregate stats) and 'scan_input'/'scan_output' (scanning 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 provides explicit usage scenarios: review scans, check compliance history, investigate flagged activity. It does not explicitly state when not to use the tool or name alternatives, but the context with sibling tools makes differentiation clear.

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

• scan_outputA
  4.6/5.0
  Behavior4/5

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

  Discloses what is scanned (PII, secrets) and return format. No annotations, but description covers main behavioral aspects. Minor omission: no mention of idempotency 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?

  Concise: a one-sentence purpose, usage instruction, and structured Args block. No wasted words; every sentence adds value.

  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?

  Despite no output schema, the description covers return values in detail. Tool is simple and well-explained; sibling tools are different, so no confusion.

  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?

  The only parameter 'text' has no schema description (0% coverage). The description's Args section provides detailed explanation of what text should contain, adding significant value.

  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 explicitly states the tool scans outgoing text for PII and secrets, using specific verbs and resources. It differentiates from sibling 'scan_input' by specifying outgoing vs incoming.

  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 clear context: use on agent-generated responses before sending, posting, or logging. Lacks explicit 'when not to use' but the context is sufficient.

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

• scan_inputA
  5/5.0
  Behavior5/5

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

  No annotations provided, but description fully discloses behavior: it scans for injection patterns and returns score, risk_level, reasons, recommendation. No side effects mentioned, consistent with a read-only scan.

  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 short paragraphs: purpose/usage, args, returns. Every sentence adds value. Front-loaded with purpose. No redundancy.

  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?

  No output schema, but description details return fields (score, risk_level, reasons, recommendation). Parameters explained. Usage guidance given. Fully covers what agent needs.

  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%. Description adds meaning for both `text` (what to scan) and `source` (origin for audit trail). Compensates fully beyond schema types and default.

  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 incoming text for prompt injection attempts.' It specifies the verb (scan) and resource (incoming text). The sibling tool `scan_output` suggests this is for input, distinguishing it well.

  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 this before an agent acts on user input, retrieved documents, tool outputs, or any other text that could contain hidden instructions.' This provides clear context and implicitly excludes scanning output (handled by sibling).

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