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

No annotations exist, so the description must carry the full burden. It fails to disclose behaviors like network requests, rate limits, what happens on vulnerability detection, or any side effects. The tool is likely a read-only check, but this is not 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?

The description is a single, front-loaded sentence with no wasted words. It efficiently conveys the tool's purpose and context.

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?

An output schema exists, reducing the need to explain return values. However, the description lacks behavioral details and parameter semantics. For a simple check tool, it is functional but not 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?

Schema description coverage is 0%. The description adds no meaning beyond parameter names. The 'ecosystem' parameter has an enum but the description does not explain its impact (e.g., which package ecosystems are supported).

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 action ('Check a package against OSV.dev') and the specific use case ('before installing an AI-suggested dependency'). It distinguishes from sibling tools like scan_dependencies which likely scans all dependencies.

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 clear context for when to use the tool ('before installing an AI-suggested dependency'). It does not explicitly state when not to use or list alternatives, 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.

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

No annotations are provided, and the description does not disclose any behavioral traits such as whether the tool is read-only, what it returns, or any side effects. It only states the detection capability, leaving significant behavioral ambiguity.

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 a single concise sentence, which is efficient but lacks any additional structure or detail. It is not verbose, but could benefit from breaking down purpose or parameters.

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 an output schema exists, the description does not clarify the role of the 'code' or 'filename' parameters, nor does it set expectations on output format or detection scope. The tool is not fully described for confident invocation.

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 0%, and the description gives no explanation of the two parameters ('code' and 'filename'). The agent cannot infer what input is expected beyond the parameter names, which is insufficient.

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 detects secrets, Korean personal information, and internal network values. This is a specific verb-resource combination that distinguishes it from sibling scanning tools which are more general.

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?

No usage guidelines are provided. The description does not indicate when to use this tool versus alternatives like scan_code or scan_path, nor does it give any context about prerequisites or limitations.

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 carry the full burden. It only states what it does, but fails to disclose any behavioral traits like error handling, authentication requirements, or performance characteristics.

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 a single concise sentence that is front-loaded and efficient. However, it may be too brief, sacrificing completeness for brevity.

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?

For a simple retrieval tool with one parameter and an output schema, the description is minimally adequate. It lacks error handling context or return value details, but given the low complexity, a 3 is appropriate.

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 0%. The description does not explain the 'rule_id' parameter beyond its name, lacking format, example, or any additional meaning. The output schema exists but is not described, adding no value.

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 returns a rule by ID, using a specific verb and resource. It is distinct from sibling tools like list_loaded_rules (which lists all rules) and search_rules (which searches by criteria), but does not explicitly differentiate.

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 no guidance on when to use this tool versus alternatives like list_loaded_rules or search_rules. It lacks any context on prerequisites, exclusions, or usage scenarios.

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 convey behavioral traits. It states 'list loaded guidance rules' but does not elaborate on side effects, permissions, or limitations (e.g., whether it shows all rules or is paginated). Minimal but acceptable for a read-only operation.

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 a single, clear sentence with no extraneous information. It is appropriately sized and front-loaded.

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 no parameters, an output schema exists to describe return values, and the operation is straightforward (list all loaded rules), the description is fully adequate for an agent to use this tool correctly.

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 tool has zero parameters with 100% schema coverage (empty schema). According to guidelines, baseline is 4. No additional parameter info is needed.

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 'List loaded guidance rules' with a clear verb and resource. It distinguishes from sibling tools like get_rule (single rule) and search_rules (search), avoiding ambiguity.

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 phrase 'for debugging and audit' provides clear context for when to use, but lacks explicit exclusions or alternative recommendations. However, the context is sufficient for a simple list tool.

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 discloses that output is self-contained and suitable for sharing, but does not mention safety traits (e.g., read-only, auth needs, rate limits). The behavioral information is partial but not misleading.

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 efficient, using bullet points for format options and a single sentence for the main purpose. It front-loads the core action. Some mixed language (Korean/English) may slightly reduce clarity but is acceptable given context.

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?

The tool has moderate complexity and an output schema, so description need not detail return values. It covers use cases and format choices well, but the lack of description for the required 'report' parameter leaves a significant gap. Overall adequate but not comprehensive.

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 0%, yet the description only adds meaning to the 'format' parameter by explaining use cases for each enum value. The required 'report' parameter is completely undocumented, leaving the agent without guidance on its structure or required fields.

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 renders a ScanReport into a Korean report, with explicit verb ('renders') and resource. It lists four output formats, distinguishing it from sibling tools like scan_code or scan_path, which are scanning 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?

The description explicitly states when to use the tool ('when a human-readable document for approval/reporting is needed') and provides detailed guidance for each format (markdown for body, html for self-contained email/PDF, sarif for CI integration). This effectively helps the agent decide between 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?

Since no annotations are provided, the description carries full burden. It discloses that code is not sent to external APIs, secrets/PII are masked with short evidence, and each finding includes 'why_it_matters' and 'safe_fix'. 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.

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

The description is two short paragraphs, front-loading purpose. It is mostly efficient but could be slightly more concise (e.g., the list of issue types could be shortened). Still, no wasted 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 the tool has 5 parameters (1 required) and an output schema, the description adequately covers behavioral aspects and return structure (masking, why_it_matters, safe_fix). However, it fails to explain optional parameters, which is a notable gap for 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?

Schema description coverage is 0% (no descriptions in input schema). The description only explains the 'code' parameter implicitly (the snippet to scan) but does not detail 'filename', 'language', 'scenario', or 'profile'. It adds value for output structure but not for parameters.

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 it scans code for security vulnerabilities (specific verb+resource) and lists types of issues. It distinguishes itself from the sibling tool 'scan_path' by specifying that 'scan_path' is for file/folder paths.

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 when-to-use (when user asks about code safety or requests a security review) and when-not-to-use (file/folder paths: use scan_path). This clearly differentiates from 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?

Discloses that only package names and versions are sent to OSV.dev, not source code. Also explains inability to parse lock files and the resulting 'unparsed' verdict. With no annotations, this level of detail is excellent.

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?

Concise and well-structured with a clear main action, privacy note, limitation, and integration tip. However, inclusion of Korean text may reduce clarity for non-Korean speakers, though it adds specific detail.

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?

Overall sufficient given the output schema exists, but the description does not cover the limit and ecosystem parameters, which are essential for correct usage. Lack of parameter documentation is a notable gap.

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?

Only manifest_text is implicitly referenced in the description. The limit and ecosystem parameters are not explained at all, and schema description coverage is 0%, so the description fails to add meaning for most parameters.

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 parses a dependency manifest and checks packages with OSV.dev. However, it does not explicitly differentiate from sibling 'check_package' which might handle individual packages.

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 guidance on input (original manifest vs lock files) and integration with scan_path and render_report, but does not explicitly state when to use this tool versus alternatives like check_package.

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?

Detailed behavioral disclosure: traverses locally, skips build/vendor dirs, ignores binaries, no external API calls for source code. Mentions findings include why_it_matters and safe_fix. No annotations provided, so description fully compensates.

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?

Well-structured with bullet points, but somewhat lengthy. Could be more concise without losing 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?

Given no annotations, description covers behavioral traits, workflow (use render_report), and constraints. Output schema exists so return values need not be explained. Comprehensive for a scanning 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 0%, but description only implicitly covers 'path'. It does not explain 'scenario', 'profile', or 'max_files' parameters, leaving gaps in meaning 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 files/folders for security compliance, using specific verb '점검' and resource 'path'. It distinguishes from sibling 'scan_code' by specifying local paths vs in-memory code.

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 (local path security check) and when not (use scan_code for code snippets). It also positions the tool as entry point for 'existing codebase audit' flow.

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 exist, so the description must disclose behaviors. It mentions that approved_only excludes auto-generated proposed rules, but lacks details on default behavior (e.g., limit is 5), pagination, read-only nature, or any side effects. The description is incomplete for a search tool with 7 parameters.

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 sentences long, front-loading the core purpose and following with actionable parameter advice. It is efficient with no redundant words. However, the brevity sacrifices coverage of other parameters, which could be included without losing conciseness.

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 7 parameters, 1 required, and an output schema exists, the description is insufficient. It misses key behavioral context such as the default limit, the nature of the 'query' field, and how to combine filters. The output schema relieves return-value explanation, but the description still lacks completeness for effective invocation.

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 0%, so the description must compensate. It adds meaning for only 2 of 7 parameters: 'approved_only' and 'status.' The critical required parameter 'query' is not described, nor are 'scenario', 'language', 'severity_min', or 'limit.' This leaves significant gaps for the agent.

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's purpose: 'Search baseline and realtime security guidance rules.' The verb 'Search' and resource 'security guidance rules' are specific. However, it does not explicitly differentiate from sibling tools like 'list_loaded_rules' or 'get_rule', relying on the search concept rather than comparative guidance.

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 gives direct usage advice for two parameters: 'Set approved_only=True to exclude auto-generated proposed rules' and 'Use status="proposed" to inspect pending rules.' This provides helpful context for specific scenarios. However, it does not guide when to choose this tool over alternatives, leaving that implied.

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?

Since no annotations are provided, the description fully discloses that it returns runtime diagnostics without network calls, indicating a safe, read-only operation. There is no mention of destructive effects, which is appropriate for a diagnostic 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 extremely concise: two sentences, front-loaded with the core purpose. Every word serves a purpose, with no redundancy or filler.

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 no parameters and an output schema exists, the description provides sufficient context: it explains the return values and the use case for health verification, making it complete for an agent to decide when to invoke it.

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?

With no parameters, schema coverage is 100% automatically. The description adds value by detailing the output (package version, rules dir, rule counts, env), which helps the agent understand what to expect, compensating for the lack of param-related information.

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 'Return runtime diagnostics' and lists specific items (package version, rules dir, rule counts, env), clearly differentiating from sibling tools like scan_code or list_loaded_rules which focus on different operations. The verb 'verify' further clarifies its diagnostic role.

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 advises using the tool from any MCP client to verify server health and see loaded rules, and notes 'No network calls', which implies it's safe and fast. However, it does not explicitly state when not to use it or mention alternatives, though the sibling tools are distinct enough.

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?

With no annotations, the description must disclose behavioral traits. It hints at safety filtering ('public-officer-friendly') but omits whether the recommendation is deterministic, requires network access, or has side effects. No details on authorization or rate limits are given.

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 very concise (one sentence). However, it omits essential information, making it incomplete rather than efficiently informative. Every word serves a purpose, but the content is insufficient.

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 presence of an output schema and two simple parameters, the description should at least define the core concept ('finding') and the role of each parameter. It fails to do so, assuming background knowledge. The tool's context is poorly captured.

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 0%, yet the description does not explain any parameter purpose or constraints. The two parameters, rule_id and unsafe_code, remain entirely undefined in the description, adding no 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 clearly states the tool returns a 'safe-fix recommendation for a finding' with a specific qualifier ('public-officer-friendly'). This uniquely identifies the tool's function among siblings like check_package or scan_code, leaving no ambiguity.

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?

No guidance is provided on when to use this tool versus alternatives (e.g., get_rule or run_scan). There is no mention of prerequisites, exclusions, or typical use cases, leaving the agent to infer usage independently.

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