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

There are no annotations, so the description carries full responsibility for behavioral disclosure. It does not explain what happens when the target is authorized or unauthorized, whether the operation is read-only, or what response the agent should expect.

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, compact sentence with no redundant words. It conveys the core purpose immediately.

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 and no behavioral details, an agent cannot know how to interpret the tool's result or how to act on it. For a preflight authorization check, this is a meaningful 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?

Schema description coverage is 100% and the target parameter already includes '域名/URL/IP'. The tool description adds no further semantic detail, so the baseline score of 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 '检查目标是否在授权测试范围内' states a specific verb (check) and a specific resource/condition (whether a target is within authorized testing scope). It clearly differentiates this from the sibling scanning, export, and configuration 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 intended use is implied: check a target before engaging in security testing. However, it does not explicitly state when to use this tool versus alternatives, nor does it mention that it should be called before other scanning 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 carries the full burden of disclosing behavior. It only states a vague scanning action with no mention of whether the scan sends HTTP requests, whether it is intrusive or safe, what rate/impact it may have, what it returns, or what permissions or side effects are involved.

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 short, but brevity here comes at the cost of substance. It reads as a title or label rather than a functional description, so it is under-specified rather than genuinely concise.

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 security scanner with no annotations and no output schema, the description is insufficiently complete. It does not explain what the scan discovers, how to interpret results, whether additional tools or permissions are needed, or what the expected output format is.

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 the baseline is 3 even though the description adds no parameter-specific meaning. The description does not clarify when to provide a custom wordlist or how extensions affect scanning, but the schema already documents each 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 '敏感目录扫描' is essentially a decorated restatement of the tool name ('sensitive directory scan') and does not explain what the tool actually does with the target URL. It neither distinguishes this tool from sibling scanners nor specifies what constitutes a 'sensitive directory' or how results are produced.

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?

There is no guidance about when to use directory-scan versus sibling tools like web-fingerprint, extract-endpoints, or vuln-scan. The description gives no context, prerequisites, exclusions, or hints about which scanning scenarios this tool is best suited for.

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 disclose behavioral traits. It only mentions the tools used, giving a hint that it may be more thorough/slower than alternatives, but it does not describe output format, side effects, rate limits, or whether it is read-only. This is a significant gap for a tool with zero annotation coverage.

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 efficiently states the purpose and tools used. It is concise and has no wasted words, though it lacks structural elements like prerequisites or usage examples.

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 that there is no output schema and no annotations, the description is incomplete. It does not explain what the tool returns, any performance implications (e.g., amass being slow), or how it differs from the lite sibling. An agent would need to open the schema and infer behavior from the tool name alone.

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 description coverage is 100%, so each parameter already has a description. The tool description adds no additional meaning beyond what the schema provides, such as how the 'tools' parameter interacts with the default behavior. Baseline 3 is appropriate when schema carries the burden.

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 states a specific verb ('enumerate') and resource ('subdomains'), and mentions the tools used (subfinder + amass). However, it does not differentiate from the sibling tool 'enumerate-subdomains-lite', so the purpose is clear but lacks sibling differentiation.

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. There is no mention of conditions, prerequisites, or the lite variant. The agent is left to infer usage from the name alone.

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 behavioral disclosure burden. It does reveal that the tool relies on the crt.sh API and needs no external tools, which implies a passive, network-dependent operation. However, it does not mention output format, rate limits, or failure modes, leaving important behavior undisclosed.

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 compact sentence with no filler. The core action is front-loaded, and the parenthetical adds genuinely new information about the method and external dependency.

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 one-parameter, read-only enumeration tool, the description is minimally viable: an agent knows what to call and with what input. But with no output schema and no stated return format, an agent cannot know what the tool will hand back, leaving a meaningful 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?

Schema description coverage is 100% and the 'domain' parameter is already explained with an example. The tool description adds no additional parameter semantics, so it sits at the baseline.

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 states a specific action and resource: '子域名枚举' (subdomain enumeration), and adds the concrete method '使用 crt.sh API' (uses crt.sh API). It stops short of distinguishing itself from the sibling tool 'enumerate-subdomains', so it loses the fifth point.

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?

There is no guidance on when to prefer this lite tool over 'enumerate-subdomains' or when to choose it instead of other enumeration/scan siblings. The parenthetical '无需外部工具' hints at one use case (no external tool installation) but never states it as a selection condition.

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 of behavioral disclosure. It only states the export purpose and does not disclose output format, side effects, whether it is a read operation, permissions needed, or any post-export behavior. For a tool with zero annotation coverage, this is a significant gap.

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 compact sentence with zero filler and the purpose is front-loaded. It is appropriately short, though the brevity sacrifices some substance that is penalized in other dimensions.

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 an export tool with no output schema and no annotations, the description should explain what form the export takes, where it is delivered, or what 'submitting to SRC' entails. It only states the high-level purpose, leaving an agent to guess about output format and side effects.

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 the schema already documents scan_id as '扫描 ID' (scan ID). The description adds nothing beyond the schema about the 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 states a specific verb and resource ('导出漏洞发现' / export vulnerability findings) plus a clear purpose context ('用于提交 SRC' / for SRC submission). It is distinguishable from most siblings like verify-cve or generate-report, though it doesn't explicitly contrast with the similarly named generate-report.

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 '用于提交 SRC' (for submitting to an SRC/Security Response Center) implies the intended use case, but no explicit when-to-use, when-not-to-use, or alternative routing is provided. Usage context is implied rather than stated.

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 of behavioral disclosure. It mentions 'from JS file analysis' which hints at the method, but doesn't disclose whether this is a read-only operation, whether it makes network requests, whether it can be rate-limited, or what the output format looks like. For a tool that crawls a website, this is a significant gap.

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 front-loads the core purpose. It's efficient and to the point, though it could benefit from a second sentence about usage 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?

For a tool that crawls JS files and extracts endpoints, the description is incomplete. It doesn't mention the output format, whether results are saved or returned, potential rate limits, or how it differs from the 'lite' sibling. With no annotations and no output schema, the description should provide more 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?

Schema description coverage is 100%, so the schema already documents both parameters. The description adds no additional meaning beyond what the schema provides. Baseline 3 is appropriate since the schema does the heavy lifting.

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 states a specific verb ('extract') and resource ('API endpoints from JS file analysis'), which clearly distinguishes it from sibling tools like port-scan or directory-scan. However, it doesn't explicitly differentiate from the sibling 'extract-endpoints-lite', which likely performs a similar function with reduced scope.

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 doesn't mention that 'extract-endpoints-lite' exists as a lighter option, nor does it specify conditions like 'use this for full analysis' or 'use lite for quick checks'. The context is implied by the name and description but not explicitly stated.

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 says 'extracts API endpoints' with no information on side effects, network usage, error conditions, or performance. It does not disclose that this might be a read-only operation or that it may require network access. The behavior is opaque beyond the basic action.

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, but it is under-specified. It is only one phrase, but it lacks critical detail. While conciseness is good, it does not earn high marks because it omits essential information that would make it useful.

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 one parameter, no annotations, and no output schema, the description is inadequate. It does not explain what the output will look like (e.g., list of endpoint URLs), any prerequisites, or limitations. The agent has to guess what 'extract' returns and how it differs from similar 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 description coverage is 100% for the single parameter 'url', which is described as '目标 URL' (target URL). The description does not add any extra meaning beyond that, but since coverage is high, the baseline of 3 is appropriate. It does not, for example, clarify URL format or whether it must be reachable.

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 states the verb 'extract' and the resource 'API endpoints', but it is vague: it does not specify what tool is avoided ('no external tool' is unclear) and does not differentiate from siblings like 'extract-endpoints' aside from the '-lite' suffix. It does not explain what 'endpoints' means in this context (URLs, paths, etc.).

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?

There is no guidance on when to use this tool versus siblings such as 'extract-endpoints' or 'directory-scan'. The phrase 'without external tools' implies a lightweight operation, but no exclusions or alternatives are mentioned. The context of when this is preferred is not conveyed.

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 of behavioral disclosure. It only says a report is generated; it does not explain side effects, whether the report is persisted, what inputs it depends on, or how long generation might take.

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 no filler words. However, it is so minimal that it provides little useful structure or information beyond the tool's name.

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 annotations, no output schema, and many sibling tools, this description is incomplete. An agent cannot tell what format the report returns, whether it is based on scan_id, or how it differs from export-findings.

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 the schema already documents scan_id, format, and include_raw. The description adds no extra meaning about these parameters, 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 states a clear action and resource: '生成侦察报告' (generate reconnaissance report). This is understandable on its own, but it does not differentiate this tool from siblings like export-findings or the scan/recon tools, and it largely restates the tool name.

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?

There is no guidance about when to use this tool versus alternatives such as export-findings or the various scan tools. No conditions, exclusions, or prerequisites are given.

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 only states the action 'get' but does not explicitly say whether the operation is read-only, what permissions might be required, or what response format to expect. This is a notable gap for a tool that could be expected to be read-only.

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 with no redundant words. It is front-loaded with the verb and resource, making it highly scannable for an agent.

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 parameterless getter, the description is minimal but adequate. It states what the tool does but does not describe the response structure or any side effects. Given the simplicity, it is reasonably complete, though it could benefit from noting that it returns the current configuration.

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, so the baseline is 4. The description correctly implies no input is needed, and no additional parameter semantics are required. This dimension is fully satisfied.

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 '获取' (get) and the resource '限流配置' (rate limiting configuration), making the tool's purpose unambiguous. It naturally distinguishes from siblings by its unique subject matter, even without explicit comparison.

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. The description gives no context for when to call it or when not to, and it does not mention any related tools. It is implied that one uses it to retrieve rate limits, but the description lacks explicit usage conditions.

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 of behavioral disclosure. It only adds that nmap is used, without explaining that this is an active network scan, potential side effects, rate-limit implications, or what the result will look like.

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, short sentence with no filler or redundancy. It is easy to parse and front-loaded, though its brevity contributes to gaps in other dimensions.

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 tool with no annotations and no output schema, the description is too sparse. It omits when this tool is preferred over port-scan-lite, the meaning of the scan_type values, expected output, and any behavioral considerations.

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%, with target, ports, and scan_type already explained in the schema. The description itself adds no parameter-level meaning beyond what the schema provides, so the baseline score 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 states 'port scanning (using nmap)', identifying the operation (scan) and resource (ports) plus the underlying engine. It is clear but does not differentiate this tool from sibling port-scan-lite or other scan-related 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?

There is no guidance about when to use this tool versus alternatives like port-scan-lite, web-fingerprint, or enumerate-subdomains. No conditions, prerequisites, or exclusions are mentioned.

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?

The description discloses the core mechanism ('TCP connection test'), which implies a connect-style scan without raw sockets. However, without annotations, it does not mention rate limits, potential security system triggers, or whether advanced privileges are needed, so the behavioral picture is incomplete.

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 short and front-loaded with the core action and mechanism. There is no wasted text, though the brevity contributes to missing guidance and behavioral 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?

Given the absence of annotations and an output schema, the description is too sparse. It does not define return values, the limitations of the 'lite' variant, or any authorization expectations. An agent could invoke it, but might not know which sibling to select or how to interpret the results.

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 the baseline is 3. The description adds no parameter-level detail beyond what the schema already provides, but the schema fully documents both host and ports with an example, so the description doesn't need to compensate.

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 states a specific verb and resource: 'simple port scan (TCP connection test)', which clearly identifies what the tool does. However, it does not explicitly differentiate from the sibling 'port-scan' beyond the 'lite' name and the word 'simple', so it lacks robust sibling differentiation.

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?

There is no guidance on when to use this tool versus the full 'port-scan' or other lite variants. The description provides no context about scenarios where the lite version is preferable, leaving the agent to infer the selection criteria.

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 full burden of behavioral disclosure, but it only repeats the action name. It does not state whether the reload is disruptive, requires authorization, returns confirmation output, or affects existing sessions.

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 with no filler or repetition. It is appropriately sized for a zero-parameter tool, though it sacrifices behavioral detail 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 zero-parameter tool this is simple, but with no output schema and no annotations, the agent is left without information about expected results, failure modes, or side effects of reloading configuration. The description is minimally usable but incomplete.

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 zero parameters and schema description coverage is vacuously 100%, so there are no parameter details the description must compensate for. The baseline of 4 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 states a specific verb ('reload') and a concrete resource ('configuration', further qualified as whitelist/asset library). This is clear enough to distinguish it from sibling scan/search/sync tools, though it does not explicitly name any sibling it is not.

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 given about when this tool should be invoked versus alternatives, nor are prerequisites or triggering conditions mentioned. An agent must infer that reloading config is appropriate after configuration changes.

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 says the tool searches assets. It does not state whether the operation is read-only, whether it checks eligibility, whether it consumes rate limits, or what happens if no assets match. This is a meaningful gap for a tool that appears to be a read/lookup 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 front-loaded clause with no wasted words; it names the action, scope, and asset categories compactly. It could include more behavioral detail, but as a pure conciseness matter it is efficient.

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 one-parameter search tool with no output schema and no annotations, the description leaves out important contextual details: what a result looks like, what sources are searched, and whether authorization or rate-limit checks apply. The description is adequate for locating the tool but not for confidently understanding its full 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%, so the schema already documents the keyword parameter and notes fuzzy matching. The description adds context by defining the asset types searched, but it does not add new meaning about how the keyword is matched or interpreted 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 states a specific verb ('search') and a resource category ('testable assets, i.e. domains/IPs/APPs'), which makes the tool's purpose understandable and distinguishes it from sibling tools like sync-src-assets or enumerate-subdomains. It could be clearer about whether 'testable' means 'in-scope' or 'verified available', but the core purpose is not ambiguous.

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 given about when to use this tool versus alternatives. The description does not mention that it is the entry point for asset discovery, nor does it exclude cases such as 'use sync-src-assets to import assets first.' The usage context is only implied by the word 'search.'

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 of behavioral disclosure. It discloses that the tool crawls/latest asset information, implying network activity, but does not state side effects such as overwriting local cached data, credential requirements, rate-limit impact, or runtime expectations. The term 'sync' suggests a mutating refresh, but the consequences are left unexplained.

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?

A single sentence that is efficiently front-loaded with the action and resource, and the parenthetical adds useful behavioral color without wasting words. There is no filler or repetition.

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 annotations and no output schema, the description leaves critical operational context unstated: what the tool returns, whether authentication is required for the SRC platform, whether the sync is destructive, and how it relates to sibling asset tools. For a tool that interacts with an external platform, this is too sparse.

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% for both parameters (force and platforms). The tool description adds no parameter-level detail beyond what the schema already provides, so the baseline score 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 uses a specific verb ('sync') and a clear resource ('SRC platform's authorized testing scope'), with a parenthetical clarifying it crawls the latest asset information. This distinguishes it from sibling query tools like search-assets, though it does not explicitly name any sibling.

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?

Usage context is implied rather than stated: 'sync' suggests this should be run to refresh the authorized asset list before other scanning operations. However, there is no explicit statement of when to use it versus alternatives like search-assets or check-authorization, and no exclusions are given.

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?

There are no annotations, so the description carries the full burden of behavioral disclosure. It does not explain what 'verify' actually does, whether it sends exploit payloads, what safe_mode changes, or potential side effects on the target. This is a significant gap for a security verification 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 with no unnecessary words. It is concise, though slightly under-specified.

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 annotations and no output schema, the description should provide more operational context. It does not describe safe_mode behavior, target requirements, expected output, or safety considerations, leaving an agent under-equipped to invoke the tool correctly in varied situations.

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 the parameters are already documented with names and basic descriptions. The tool description adds no extra semantic detail, but the baseline of 3 applies because the schema handles parameter meaning.

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 says the tool verifies a specific CVE vulnerability against a target, which states the verb and resource accurately. However, it does not explicitly distinguish this from sibling scanning tools like vuln-scan-lite, so it misses the top score.

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 instead of alternatives, no prerequisites, and no exclusions. The word 'specific' only implies a narrow use case; it does not explain how to choose among the many 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?

With no annotations, the description bears the full burden of behavioral disclosure. It mentions built-in payloads and no external tools, but it does not disclose that the scanner sends HTTP requests, may actively probe the target with malicious payloads, could be intrusive, or may require authorization. This is a significant gap for a vulnerability-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?

The description is a single compact sentence with no filler. The main purpose is front-loaded, and the parenthetical adds a meaningful constraint about internal payloads and external dependencies.

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 five parameters, no output schema, and no annotations, so the description should explain what the scan returns, what side effects it has on the target, and when it should be used. The one-sentence description leaves all of that implicit, making it incomplete for an agent to confidently invoke the tool in a real remediation or scanning workflow.

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 the schema fully documents the URL and all boolean check toggles. The description adds no parameter-level meaning beyond confirming that payloads are built in, which is acceptable given the schema already carries the parameter details.

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 identifies the tool as a lightweight vulnerability scanner, using a specific verb/resource ('漏洞扫描') and adding a qualifier ('轻量级', '内置 payload，无需外部工具'). It is distinguishable from sibling tools like port-scan-lite and web-fingerprint-lite because it targets vulnerabilities generically, though it could be more explicit about which vulnerability classes it covers.

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 '轻量级' and '无需外部工具' implies the tool is for quick or self-contained scans where external tools are unavailable. However, there is no explicit when-to-use or when-not-to-use guidance, and no comparison to alternatives such as verify-cve or the other '-lite' scanners.

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?

Annotations are absent, so the description carries the full burden of behavioral disclosure. It only mentions 'detection', implying a read-only operation, but does not explicitly state any behavioral traits such as HTTP requests, non-destructiveness, rate limits, or output format. This leaves the agent guessing.

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 brief (one phrase) and front-loaded with purpose, but it lacks any structural elements like usage hints or nuance. While there is no wasted text, the brevity results in under-specification rather than effective 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 a sibling with a similar name ('web-fingerprint-lite') and no annotations or output schema, the description should clarify its scope, differentiate from alternatives, and indicate the 'deep' parameter's impact. None of this is present, leaving gaps that could cause incorrect usage.

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% for both parameters, so the schema already documents their meaning. The description adds no additional semantic context beyond the schema, so it meets the baseline for adequate parameter handling without providing extra 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 states the specific verb '识别' (identify) and resource 'Web' with elaboration '技术栈检测' (technology stack detection), making the core function clear. However, it does not distinguish this tool from its sibling 'web-fingerprint-lite', so it falls short of the highest clarity tier.

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 like web-fingerprint-lite. The description only states the purpose without any context for selection or prerequisites.

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?

Annotations are absent, so the description bears full responsibility for behavioral disclosure. It only says it performs fingerprint identification and is implemented in pure Node.js; it does not mention whether it sends network requests, is read-only, has rate limits, or what side effects it may have on the target.

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 compact phrase, front-loaded with the main purpose ('web fingerprint identification') followed by the implementation detail. There is no filler or redundancy, though it is barely a sentence.

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 and very little information, the agent is left uncertain about what the tool returns, how to interpret results, and why to choose this over the sibling 'web-fingerprint'. The description is too thin for a security-scanning tool that may have operational implications.

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 100% of parameters and describes 'url' as '目标 URL' (target URL), which is straightforward. The description adds no additional meaning about format, required scheme, or edge cases, so it meets the baseline but provides no extra 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 states a clear verb+resource: 'Web 指纹识别' (web fingerprint identification), which identifies web technologies/applications. It adds the implementation detail 'pure Node.js implementation', but it does not clarify what exactly is fingerprinted or how the 'lite' variant differs from the sibling 'web-fingerprint'.

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 'web-fingerprint' or other lite tools. The only contextual hint is the 'pure Node.js' implementation, which implicitly suggests a standalone lightweight version, but no explicit conditions, alternatives, or exclusions are given.

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