AIShield Security Scanner

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

No annotations are provided, leaving the description to carry the full burden of behavioral disclosure. The description does not mention whether the scan is read-only, what it does with the inputs, what it returns, or any side effects. It only states the basic action without behavioral details.

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 sentence that is front-loaded with 'Agent-First quick scan' and contains no filler. It efficiently communicates the scope and the key differentiator of not requiring a URL.

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 tool is simple and the schema describes all parameters, there is no output schema and no annotations. The description does not explain what the scan returns, what behavioral traits it has, or what 'quick scan' entails beyond its inputs. This leaves gaps for an agent deciding how to invoke and interpret the 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 description coverage is 100%, so parameters are already well-documented. The description adds the context that source_url is for 'deep scan' (though the schema also says that), and confirms that name and description are required. It does not add substantial meaning beyond the schema, so a 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?

The description clearly states the tool's function: 'quick scan' with the verb 'scan' and resource 'a tool by name and description'. It distinguishes from deep scans by explicitly noting 'no source URL required', which differentiates it from sibling tools that might require URLs. This makes the purpose specific and clear.

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 implies usage for quick scans when only name and description are available, but it does not explicitly mention when to use this tool versus alternatives or provide exclusions. The phrase 'no source URL required' suggests a quick path, but no alternative tool is named.

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 of behavioral disclosure. It mentions that the call 'register[s] an Agent' and returns credentials, but does not explicitly state this is a mutating action, whether prior authentication is needed, or any side effects (e.g., resource creation, potential costs). This is a significant gap for a registration 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 a single, front-loaded sentence that conveys the core value proposition without redundancy. Every phrase ('Agent-First', 'one-click', deliverables) adds relevant information, making it highly concise 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?

Given no output schema, the description partially addresses return values by mentioning DID, API Key, and quick start guide. However, it lacks context about prerequisites, authentication, or what happens after registration. For a simple onboarding tool this is adequate, but not fully complete for an agent that needs to handle edge cases.

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?

All three parameters (owner, agent_name, capabilities) are documented in the schema with descriptions, meaning schema coverage is 100%. The description adds no extra parameter context, so the baseline score of 3 is appropriate; it does not compensate with additional meaning 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's purpose: 'register as an Agent' and lists deliverables (DID + API Key + quick start guide) in a single call. This specific verb+resource combination distinguishes it from sibling scanning tools like agent_quick_scan and aishield_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?

The phrase 'Agent-First one-click onboarding' implies use for initial registration/setup, but there is no explicit guidance on when to use this versus alternatives, nor any exclusion criteria. Since sibling tools are clearly scanning-related, the context provides implicit differentiation, but the description itself lacks direct usage instructions.

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 only says 'detection', which implies a read-only operation, but it does not disclose return format, whether it modifies any data, rate limits, or permissions. For a tool with no annotations, this is insufficient behavioral 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?

The description is extremely concise, consisting of only 5 words, which is compact by design. However, it lacks structured information such as usage contexts or parameter hints. It is not tautological, but it is under-specified for a tool description, sacrificing substance 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?

Given the tool has 2 parameters, no output schema, and no annotations, the description should provide more context about what the agent can expect from the tool's output or behavior. The description only covers the core purpose, leaving out return values, error scenarios, or how the platform options affect output. It is marginally sufficient but falls short of being 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?

The input schema describes 'text' but platform is only an enum without a description. The phrase '6 platform rules' adds meaning by indicating that the platform parameter controls which set of rules are applied, providing context beyond the raw enum values. Schema description coverage is 50%, and the description partially compensates by explaining the relevance of the platform 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?

The description explicitly states 'Chinese banned words detection', which clearly indicates the tool's purpose of detecting banned words in Chinese text. The addition of '6 platform rules' distinguishes it from sibling tools like aishield_scan or aishield_prompt_check by specifying platform-specific rule sets (douyin, xiaohongshu, wechat, weibo, bilibili, kuaishou). This is a specific noun phrase rather than a full verb, but the intent is unambiguous.

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. It does not mention scenarios, prerequisites, or exclusions. The mention of '6 platform rules' implies it is for checking text against platform-specific banned word lists, but it does not explicitly state when an agent should choose this over aishield_scan or aishield_prompt_check.

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 carries the full burden of behavioral disclosure. It mentions a 'pass/block verdict' but does not explain the effect of the auto_block parameter, whether the tool modifies anything, or what triggers a block. The description adds minimal context beyond the tool name.

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 short and front-loaded, with no unnecessary words. However, it is under-specified, so the brevity does not serve clarity. It earns a mid score for being concise but incomplete.

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 auto_block parameter with default behavior and no output schema, the description should explain how the verdict is used and the role of auto_block. It does not, leaving the tool's behavior underspecified for an 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?

The description does not mention any parameter behavior. Schema coverage is 50%, leaving auto_block undocumented. The source_url's purpose is clear from the schema, but the description adds no additional meaning, so it fails to compensate for the missing auto_block semantics.

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 'Pre-install safety check — pass/block verdict' clearly indicates the tool performs a safety evaluation before installation and outputs a verdict. It is more specific than a mere restatement of the name, though it doesn't explicitly differentiate from sibling scanning tools like aishield_scan or aishield_rug_pull.

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 'pre-install' implies the tool is used before installing something, providing a clear context. However, there is no explicit guidance on when not to use it or how it compares to similar sibling tools, leaving some ambiguity.

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 provided, the description carries the transparency burden. It discloses that the tool performs an HTTP handshake (network activity) and analyzes config for specific concerns. However, it does not state whether the tool is read-only, whether it sends any data, or what side effects (e.g., external requests) may occur beyond the handshake attempt.

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 sentence with an em-dash lead-in that front-loads the primary purpose. It lists multiple checks efficiently without redundant phrases. Slightly longer than ideal but every clause adds substance, so it earns a 4.

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 is complex (multiple analyses and an HTTP handshake) yet there is no output schema and the description omits what the caller receives (e.g., a report, pass/fail status). It also does not address failure modes (e.g., unresponsive server) or prerequisites. With no annotations, this is a significant gap in context.

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 input schema has one parameter (source_url) with 100% description coverage ('GitHub repo URL'). The tool description adds no supplementary meaning to the parameter, such as format examples, constraints, or relationship to the handshake. Baseline of 3 applies since schema covers the 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?

The description clearly states a specific verb ('verify', 'analyze', 'detect') and resource ('MCP config', 'HTTP handshake'). It distinguishes itself from sibling tools by enumerating unique checks (npx auto-install, sensitive env vars, oversized tool descriptions), making its purpose unambiguous.

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 explicit guidance on when to use this tool versus alternatives. The description implies usage for MCP handshake verification but does not mention any exclusions or compare with sibling tools like aishield_scan or aishield_rug_pull. The agent is left to infer applicability.

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 carry the full burden of behavioral disclosure. It states the tool checks for prompt injection and supports Chinese/English, but it does not reveal whether it is read-only, what output format to expect, or any side effects or limitations. This is a significant gap for a detection 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 a single concise phrase ('Prompt injection detection — Chinese + English') that is front-loaded and contains no wasted words. It is immediately scannable and to the point.

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 is simple, but because there is no output schema, the description should explain what the check returns or how to interpret the result. It does not, so an agent is left guessing about the response format or how this differs from sibling scan tools. This makes the description incomplete for fully autonomous use.

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 already provides 100% parameter coverage with a description for the single 'prompt' parameter (min 10 chars). The description adds value by specifying that detection targets Chinese and English text, which is useful contextual meaning 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 core function as 'Prompt injection detection' and adds the language scope (Chinese + English), making the purpose evident. However, it does not explicitly differentiate from sibling tools like aishield_scan or aishield_guardrail, so it falls short of full distinctiveness.

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 sibling alternatives. The only constraint is the schema's min 10 chars requirement, but there is no context on scenarios, exclusions, or relationship to other 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?

With no annotations, the description explains the core behavior—checking recent commits for suspicious changes—but it does not disclose side effects, read-only status, or any limitations. It adds some behavioral context beyond the name but lacks the fuller disclosure expected without annotations.

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 sentence with an em-dash, front-loading 'Rug pull detection' and then elaborating. It is concise and avoid redundancy—every word 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?

The one-parameter tool has a clear description, but without an output schema or annotations, the description does not state what the tool returns (e.g., a risk score or boolean). It also lacks usage guidance, making it minimally viable but not fully 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?

The input schema already covers the single parameter (source_url) with a clear 'GitHub repo URL' description, so schema coverage is 100%. The tool description does not add extra meaning about the parameter beyond implying it is the repository to inspect, so baseline 3 applies.

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 the specific noun phrase 'rug pull detection' and explains it as checking for removed security code or added suspicious changes in recent commits. This clearly distinguishes it from generic scanning tools like aishield_scan by giving a concrete, specific purpose.

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 implies the tool should be used when you want to verify a tool hasn't been maliciously altered in recent commits, but it does not explicitly contrast it with sibling tools or state when not to use it. No alternatives are mentioned, so guidance is only implicit.

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 carries the full burden of behavioral disclosure, but it only provides rule count and scoring dimensions. It does not mention whether the scan is read-only, what it returns, any side effects, permission requirements, or rate limits, leaving critical operational behavior opaque.

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 redundant words. It efficiently communicates the key differentiators (OWASP alignment, 133 rules, 5-dimension scoring) in a compact form. It lacks structured sections but is appropriately sized for a brief summary.

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 description is incomplete for a security scan tool with no output schema and no annotations. It fails to explain what the 5 dimensions are, what the scan results look like, or any operational context. An agent would struggle to know when to invoke this tool and what to expect from 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?

The description adds no parameter-specific meaning beyond the schema. Schema coverage is 67% (name and source_url have descriptions, tool_type does not), and the description does not elaborate on how to fill source_url or what the tool expects. The 'OWASP MCP Top 10' hint vaguely implies source input type but is not explicit.

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 is a security scan tool aligned with OWASP MCP Top 10, backed by 133 rules and 5-dimension scoring, which specifies its scope and differentiates it from a generic scan. However, it does not explicitly name the resource being scanned (e.g., GitHub repo or MCP server), though source_url in the schema hints at repository scanning. It distinguishes from siblings like agent_quick_scan by emphasizing a comprehensive, standards-aligned approach.

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 offers no guidance on when to use this tool versus alternatives such as agent_quick_scan or when not to use it. There are no contextual cues, prerequisites, or exclusions, leaving the agent without decision criteria for tool selection.

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