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

With no annotations, the description must convey behavioral traits. It states the tool 'detects' vulnerabilities, implying a read-only operation, but does not explicitly confirm it does not modify files, require specific authentication, or have rate limits. The description adds some context but lacks comprehensive behavioral disclosure.

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

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

The description is two concise sentences with no fluff. The first sentence states the purpose and capabilities, the second provides usage guidance. Every sentence adds value.

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

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

While the description explains purpose and usage well, it does not describe the output format or return values. Since no output schema is provided, the description should cover what the tool returns (e.g., list of findings). This gap limits completeness.

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

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

The schema covers all three parameters with descriptions, resulting in 100% coverage. The description does not add new information beyond the schema for each parameter, so the baseline of 3 is appropriate.

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

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

The description clearly states the verb 'Audit' and the specific resource 'Agent-to-Agent communications'. It lists precise detections (infinite delegation loops, privilege escalation, data leakage, unauthorized handoffs) and explicitly lists supported protocols, distinguishing it from sibling tools like inkog_scan which cover broader scanning.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states 'Use this when building or reviewing multi-agent systems to detect delegation vulnerabilities,' providing clear context for when to use the tool. However, it does not explicitly mention when not to use it or compare with alternative sibling tools.

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

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

No annotations are provided, so the description must fully disclose behavior. It mentions analyzing permissions, data flow risks, input validation, and vulnerabilities, which is good. However, it does not describe the output format (e.g., report, findings) or any side effects (e.g., network calls, no modifications).

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

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

The description is three sentences, front-loaded with the action, then details, then usage guidance. Every sentence adds value with no wasted words.

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

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

Given 2 parameters with full schema coverage and no output schema, the description is fairly complete. It covers purpose, scope, and usage. The only gap is the absence of output description, which would aid in an agent's decision-making.

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

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

Schema coverage is 100% with clear descriptions and examples. The tool description reinforces the parameter duality ('from the registry or GitHub'), adding contextual value beyond the schema.

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

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

The description uses a specific verb ('audit') and resource ('MCP server') with clear scope ('from the registry or GitHub'). It differentiates from sibling tools by focusing on MCP server security, while siblings like inkog_skill_scan and inkog_audit_a2a target other areas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use: 'before installing any new MCP server to verify it is safe.' This provides clear context but does not explicitly exclude alternatives or mention 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.

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

No annotations are provided, so the description carries full burden. It states it 'Analyzes agent code and maps findings to regulatory requirements' but does not disclose behavioral traits like side effects, permissions, rate limits, or output structure. Lacks depth 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.

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

Two sentences, front-loaded with the core purpose and regulatory scope. Every sentence is meaningful with no wasted words.

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

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

With no output schema, the description could better describe the nature of the report (e.g., structure, risk levels). It explains what the tool does but not what to expect from the result. Complex enough that more detail would help, but the 3 parameters are well-documented.

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

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

Schema description coverage is 100%, so baseline is 3. The description adds context about analyzing code and regulatory mapping, but does not provide additional parameter-specific meaning beyond what the schema already offers.

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

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

Clearly states it generates compliance reports for specific regulatory frameworks (EU AI Act, NIST AI RMF, etc.) and analyzes agent code. The description distinguishes this tool from siblings like inkog_mcp_scan or inkog_deep_scan by focusing on compliance mapping.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit usage context: 'Use this when preparing AI agents for regulatory compliance or audit.' Does not mention when not to use or alternatives, but the guidance is clear and actionable.

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

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

No annotations provided, so description carries full burden. Discloses scan duration (~10 minutes) and role requirement, but does not confirm read-only nature or potential side effects. While 'scan' implies non-destructive, explicit statement would improve transparency.

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

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

Compact three-sentence description: purpose, capability, and key usage notes (role, duration). Front-loaded with core functionality, no redundant or filler content.

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

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

Covers essential aspects for a scan tool: purpose, detection capability, prerequisites, and timely warning. Lacks mention of output format or result handling, but no output schema exists and siblings may follow common patterns.

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

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

Schema coverage is 100% with clear descriptions for both parameters (path and agent_name). The description adds no additional semantic meaning beyond the schema, meeting the baseline expectation for high coverage.

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

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

Clearly states it performs a deep scan using advanced analysis to detect complex vulnerabilities and logic flaws, distinguishing from pattern-based scanning. Explicitly requires the Inkog Deep role, differentiating from sibling tools like inkog_scan.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides context for when to use (for complex issues) and prerequisites (requires Inkog Deep role). Includes important temporal information (10 minutes) and user communication requirement. However, does not explicitly state when not to use or compare to alternatives like inkog_scan for faster results.

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

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

No annotations provided, so description carries full burden. It discloses return content (explanation, remediation, code examples) but does not mention limitations like what happens if finding ID is invalid or pattern unrecognized. Adequate but could be more thorough.

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

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

Two sentences, each serving a distinct purpose: first defines tool's function and content, second provides usage timing. No superfluous words; efficient and well-structured.

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

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

Tool has two optional parameters and no output schema. Description covers tool's purpose and return content adequately. Could hint at behavior when both parameters are provided vs. one, but overall complete for a simple lookup tool.

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

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

Schema coverage is 100%, so baseline is 3. The description does not add significant meaning beyond schema; it mentions 'finding or pattern' but schema already describes parameters. No added constraints or usage hints.

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

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

The description clearly states the tool provides detailed explanation and remediation guidance for security findings/patterns, listing specific content (issue, danger, fixes, code examples). It distinguishes from sibling scanning tools by advising use 'after scanning.'

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says 'Use this after scanning to understand how to fix security findings,' providing clear context. Does not mention when not to use or compare to alternatives among siblings, but the guidance is sufficient.

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

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

No annotations are provided, so description carries full burden. It implies analysis of a codebase (path required) but does not disclose potential side effects like file system access, scan duration, or that it is a read-only operation. 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.

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

Three concise sentences that front-load the action and purpose. 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.

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

Given the tool has 3 parameters, no output schema, and no annotations, the description covers the core purpose, supported formats, and usage context. It could be improved by describing the output format or behavior for invalid paths, but it is largely complete.

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

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

Input schema has 100% description coverage, so baseline is 3. The description adds minimal parameter nuance beyond what's in the schema, e.g., mentioning 'CycloneDX and SPDX formats' but those are already enumerated in the format parameter.

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

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

Description clearly states the tool generates a Machine Learning Bill of Materials (MLBOM) for AI agents, listing models, tools, data sources, frameworks, and dependencies. It also mentions supported formats (CycloneDX, SPDX), making the purpose specific and distinct from sibling audit/scan tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says 'Use this when documenting AI agent dependencies for supply chain compliance,' providing clear context. However, it does not mention when not to use or suggest alternatives.

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

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

No annotations provided, so description carries full burden. It discloses deep mode duration (10 min), detection capabilities, and frameworks mapped. Lacks details on output format but sufficient for a scanning tool.

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

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

Three sentences, front-loaded with purpose, then details, then alternative tool. No wasted words, well-structured for quick comprehension.

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

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

No output schema, but description mentions vulnerability types and frameworks. Good for a scan tool with 3 params. Could mention return type but minimal gap given sibling tools.

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

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

Schema coverage is 100%, baseline 3. Description adds context: examples for server_name, clarifies repository_url is GitHub, explains deep mode effect and duration. Value-added beyond schema.

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

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

The description clearly states the tool scans MCP servers from registry or repository URL for security vulnerabilities, listing specific types and differentiating from sibling inkog_skill_scan.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use (MCP server scanning) and when not (skill packages, directing to inkog_skill_scan). Also provides guidance on deep mode with time estimate.

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

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

No annotations provided. Description describes what it scans for but does not disclose behavioral traits like network calls, resource impact, or required permissions. It is likely read-only but not explicitly stated.

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

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

Two sentences, 60 words, front-loaded with purpose. No wasted words. Efficiently communicates key information.

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

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

Despite no output schema and no annotations, the description adequately covers tool purpose, target vulnerabilities, supported frameworks, and usage scenario. Missing return value details but schema covers output format.

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

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

Schema coverage is 100%, with clear descriptions for all 5 parameters. Description adds little beyond summarizing the scanning purpose. Baseline 3 is appropriate.

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

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

Description clearly states it is a security copilot for AI agent development, scanning for specific vulnerabilities. It distinguishes itself from siblings like inkog_mcp_scan by focusing on general AI agent frameworks, but does not explicitly differentiate from other scan tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit usage context: 'Use this whenever building, reviewing, or deploying AI agents to catch security issues before they reach production.' Does not mention when not to use or alternatives like inkog_deep_scan.

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

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

No annotations are provided, so the description carries the full burden. It discloses that deep=true takes ~10 minutes and catches novel threats. It lists vulnerability types but does not mention rate limits, auth needs, or side effects. This is sufficient for a scan tool.

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

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

The description is concise, with only a few sentences front-loaded with the main purpose. Every sentence adds value, and there is no repetition or wasted words.

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

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

Given the complexity of scanning for multiple vulnerabilities and the absence of an output schema, the description is fairly complete. It explains what it does, what it detects, and how to use it. However, it could mention the return format (e.g., a report of findings) to fully inform the agent.

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

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

Schema description coverage is 100%, and the description adds context for the 'deep' parameter ('AI-powered deep analysis (~10 min, catches novel threats)'). The other parameters are standard and well-described in the schema.

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

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

The description explicitly states the tool 'scans SKILL.md packages and agent tool definitions for security vulnerabilities' and lists specific vulnerability types, mapping to OWASP frameworks. It also distinguishes from the sibling tool inkog_mcp_scan for MCP server scanning.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides a clear alternative: 'For MCP server scanning, use inkog_mcp_scan instead.' It also explains when to set deep=true for deep analysis. However, it does not mention prerequisites or when not to use the tool beyond the MCP distinction.

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

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

No annotations are provided, so the description carries full burden. It does not explicitly state whether the tool is read-only, modifies any files, or requires network access. The detection examples imply it is a static analysis tool, but this is 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.

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

The description is concise with four sentences covering purpose, examples, compliance context, and usage guidance. No unnecessary words, but could be slightly tighter by merging sentences.

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

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

Given no output schema, the description fails to explain what the tool returns (e.g., list of mismatches, pass/fail, report). For a verification tool, this is a significant omission, making it incomplete for an agent to fully understand behavior.

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

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

Schema coverage is 100% with the path parameter described adequately. The description reinforces the purpose of the path but adds no new parameter details beyond what the schema provides, giving a baseline of 3.

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

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

The description clearly states the tool validates AGENTS.md declarations against code behavior with specific examples of governance mismatches. It distinguishes itself from sibling scanning/audit tools by focusing specifically on governance compliance.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit usage guidance: use when an AGENTS.md file exists or before deployment for compliance verification. While it lacks explicit when-not-to-use or alternatives, the context is clear.

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