Server Quality Checklist

Tool Scores

• redact_phiC
  2.9/5.0
  Behavior2/5

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

  With no annotations provided, the description carries full burden for behavioral disclosure. It states redaction with placeholders, but does not detail what types of identifiers are detected, how aggressive the redaction is, or whether the operation is reversible. No information about error cases 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.

  Conciseness4/5

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

  The description is a single sentence, front-loading the core action and output. Every word contributes to purpose, though it sacrifices completeness for brevity.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness2/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given the moderate complexity (2 params, no output schema), the description lacks context about return values, error handling, or what happens when no PHI is found. It is minimal and leaves significant gaps for an AI agent.

  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 schema already documents both parameters. The description adds no additional meaning beyond stating 'with placeholders' which aligns with the mode const. This matches the baseline of 3 for high schema coverage.

  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 purpose: detecting and redacting PHI-like identifiers with placeholders. It distinguishes from siblings by specifying the action (redact vs. scan, validate, audit). However, 'PHI-like identifiers' is somewhat vague and could be more specific.

  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 provides no guidance on when to use this tool versus its siblings (e.g., scan_phi, validate_no_phi, audit_deidentification). There is no mention of prerequisites, limitations, or alternative tools.

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

• scan_phiC
  2.9/5.0
  Behavior2/5

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

  With no annotations, the description should cover behavioral aspects like side effects, auth needs, or data handling. It only states basic functionality, omitting important traits such as whether the tool is read-only or if it modifies data.

  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 single, focused sentence with no extraneous information. It efficiently conveys the core purpose.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness2/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Despite the tool's simplicity, the description fails to specify the format or content of the 'structured findings' output. Without an output schema, the agent lacks crucial context about what to expect from the tool.

  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 input schema fully describes the 'text' parameter with a clear description, and the tool description does not add further meaning. Given 100% schema coverage, 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 clearly states it detects PHI-like identifiers and returns structured findings, which differentiates it from siblings like audit, redact, and validate. However, it does not explicitly clarify the distinction from validate_no_phi, though detection vs validation is implied.

  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?

  No guidance is provided on when to use this tool versus the sibling tools. The description only states the tool's function, leaving the agent without context for appropriate use cases.

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

• validate_no_phiB
  3.2/5.0
  Behavior2/5

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

  With no annotations, the description carries full burden but only states the purpose. It does not disclose return behavior (e.g., boolean, error), side effects (read-only? destructive?), or what constitutes 'detected' (string matching? ML model?). This lacks essential behavioral details for safe invocation.

  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 sentence that efficiently states the core purpose. It is well-structured and front-loaded with the verb 'Validate'. However, it misses opportunities to include critical invocation context without becoming verbose.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given the simplicity (1 parameter, no output schema, no annotations), the description is minimally adequate but leaves gaps: no mention of return type, error cases, or where this fits in a workflow. For a validation tool, this is incomplete for an agent to use confidently.

  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%: the single parameter 'text' has a clear description ('Plain text to inspect.'). The tool description adds no further meaning beyond the schema, so baseline 3 applies. No improvement or degradation.

  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 action ('validate') and the condition ('text has no detected PHI-like identifiers'). It distinguishes the tool from siblings (audit_deidentification, redact_phi, scan_phi) by focusing on validation rather than auditing, redaction, or scanning.

  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?

  No guidance is provided on when to use this tool vs alternatives. For example, it doesn't specify whether this should be called before redaction or scanning, or what the expected input/output context is. The description only states what it does, not when or why to choose it.

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

• audit_deidentificationA
  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 full burden. It indicates a read-only inspection but lacks details on side effects, authentication needs, or what 'limitations' refer to.

  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 single, focused sentence with no unnecessary words, making it highly concise and front-loaded.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given the simplicity (one parameter, no output schema), the description provides the core purpose but lacks details on the output format or what 'limitations' means, leaving some gaps.

  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 parameter 'text' has a schema description of 'Plain text to inspect.' The tool's description adds meaning by specifying it inspects for PHI identifiers and limitations, going beyond the 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 the tool's purpose: returning an audit-oriented summary of PHI-like identifiers and limitations. It distinguishes from siblings like redact_phi, scan_phi, and validate_no_phi by focusing on auditing rather than action.

  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 implies the tool is for audit purposes but does not explicitly state when to use it over alternatives or when not to use it. No exclusions or alternate tools are mentioned.

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