Server Quality Checklist

Tool Scores

• revoke_or_disable_app_registrationC
  2.7/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden. It discloses that the tool only generates dry-run commands rather than executing them, which is key. However, it fails to mention other behaviors like authentication requirements, error handling, or output format.

  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, concise sentence. It front-loads the key concept (dry-run generation) without extraneous detail, making it easy to read. However, it could benefit from brief bullet points for clarity.

  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 tool has 3 parameters, an enum, and no annotations, the description is too sparse. It omits the output format, error scenarios, and prerequisites. The existing output schema is not referenced, so the agent lacks complete context.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters2/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 0%, so description must add meaning. It mentions 'disable sign-in or revoke credentials' which maps to some action enum values but not all. It does not explain the app_id or key_id parameters, leaving their semantics unclear.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose3/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description states it generates dry-run commands for disabling sign-in or revoking credentials, but the action enum includes additional actions like remove_permission and rotations, which are not mentioned. It identifies the verb 'generates' and the resource 'app registration commands', but misses full scope.

  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 on when to use this tool versus siblings like audit_app_registrations or generate_remediation_plan. The description implies it's for generating remediation commands, but without explicit context, the agent may misuse it.

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

• run_posture_scanB
  3.2/5.0
  Behavior3/5

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

  The description discloses that scans run concurrently, results are combined and optionally filtered, and a shared cache is updated. However, with no annotations, it lacks details on side effects (e.g., whether scans modify data), permissions needed, or runtime implications.

  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 two sentences long, with the first sentence providing the core action and the second adding cache update context. It is concise and front-loaded, but could include parameter details without becoming verbose.

  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 tool has 5 parameters, no annotations, and no schema descriptions, the description is insufficient for correct invocation. It lacks parameter explanations, usage context, and behavioral details beyond the basic operation.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters1/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  With 0% schema description coverage, the description does not explain the parameters. Terms like app_id, rule_id, severity, and expiry/duration fields are mentioned only as parameter names, so the description adds no meaning beyond the names themselves.

  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 runs app registration and Conditional Access scans concurrently and returns a combined, optionally filtered PostureScanResult. It also mentions updating a cache, which distinguishes it from sibling tools like 'audit_app_registrations' and 'scan_conditional_access_gaps' that likely run single scans.

  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 running both scan types together and filtering results, but it does not explicitly state when to use this tool versus the individual sibling tools or provide any when-not scenarios.

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

• generate_remediation_planA
  3.5/5.0
  Behavior3/5

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

  No annotations provided, so description bears full burden. It accurately states the tool generates a report and CLI commands, but omits details about side effects, required permissions, or whether the report is persisted. The description is not misleading but lacks depth.

  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 directly conveys purpose without superfluous words. It is concise but could benefit from slight restructuring to front-load key actions.

  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 tool has one required parameter and no annotations, the description is minimally adequate. The existence of an output schema partly compensates, but the description does not elaborate on what the returned report or commands contain.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters2/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 0% for the only parameter 'issues', and the description adds no additional meaning beyond the schema type definition. It says 'from findings', but does not explain what the issues array should contain (e.g., structure, required fields).

  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 generates a Zero-Trust Markdown security report and dry-run CLI remediation commands. It distinguishes from sibling tools like audit_app_registrations, scan_conditional_access_gaps, and revoke_or_disable_app_registration by focusing on plan generation rather than auditing, scanning, or revoking.

  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 usage 'from findings' but does not explicitly state when to use this tool vs. alternatives. No exclusion criteria or prerequisites are mentioned, leaving the agent to infer context from sibling names.

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

• audit_app_registrationsA
  3.6/5.0
  Behavior3/5

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

  No annotations are provided, so the description must convey behavioral traits. It mentions scanning and returning results but does not state whether the tool is read-only, requires specific permissions, or has side effects. For a security audit tool, read-only behavior is likely but not confirmed.

  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 two sentences long, front-loads the core purpose, and contains no unnecessary words. Every phrase adds value: the scanning targets and the output structure are clearly stated.

  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?

  The description adequately covers the tool's purpose and output (structured findings + summary), and the presence of an output schema reduces the need for return value details. However, the lack of parameter descriptions and usage context leaves gaps in completeness for a tool with two configurable thresholds.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters2/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The description does not mention the two parameters (imminent_expiry_days, excessive_lifespan_days) or explain their meaning. With 0% schema description coverage, the description should compensate, but it only hints at the concepts (expiring, excessive) without connecting them to the parameters. The agent must infer from parameter names 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 the tool scans Entra ID app registrations for specific issues (expiring secrets, excessive lifespans, risky permissions, insecure redirect URIs) and returns structured findings with a summary. This distinguishes it from sibling tools like scan_conditional_access_gaps or run_posture_scan.

  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 usage when auditing app registration security but provides no explicit when-to-use guidance, conditions, or alternatives. Given siblings exist for similar tasks, some direction would help an agent decide between this and other audit tools.

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

• scan_conditional_access_gapsA
  3.6/5.0
  Behavior2/5

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

  No annotations provided, so description must fully disclose behavior. It states 'scans' and 'returns structured findings' but does not explicitly state it is read-only. No mention of authentication, rate limits, or scope (e.g., all policies or filtered). Even though it's a scan, the agent cannot be sure it doesn't trigger actions.

  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 sentences, minimal waste. Each sentence adds value: first states action and targets, second describes output format. 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?

  For a no-parameter tool with output schema, the description covers the core purpose and output format. It specifies exactly what it checks (admin MFA exclusions, report-only mode). Could mention it is safe to run frequently, but given low complexity, it is mostly complete.

  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?

  Zero parameters, schema coverage 100%. Baseline per rule is 4. Description adds no parameter info, but none needed. The tool operates without inputs, so clarity on purpose is sufficient.

  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 identifies the tool scans Entra Conditional Access policies for specific security gaps (admin MFA exclusions, report-only mode). It distinguishes from siblings like audit_app_registrations (different resource) and run_posture_scan (broader scan). Verb 'scans' + resource 'Entra Conditional Access policies' + specific focus.

  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 explicit guidance on when to use this tool versus siblings. Given sibling names like run_posture_scan (broader security scan) and audit_app_registrations (audit of app registrations), the description should state when to choose this tool (e.g., for CA-specific gap analysis). The AI agent lacks decision context.

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