stagenth · 网页数据

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

Discloses billing (1 credit per page), SSRF validation per page, non-blocking failure handling, and no AI generation. However, missing details like rate limits, concurrency, or data retention, which would further aid agent selection.

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

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

Two short, front-loaded sentences with no superfluous words. First sentence defines core purpose and billing; second adds key behavioral details. Every sentence serves a purpose.

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?

Missing output explanation (what does the Markdown look like?); no mention of cancellation, timeouts, or result structure. For a tool with no output schema, the description should describe the return value format to ensure correct agent 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 covers all 4 parameters with descriptions. The tool description adds billing context but does not enrich parameter meaning beyond what the schema already provides. Baseline 3 is appropriate for 100% schema coverage.

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

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

Description clearly states it crawls multiple pages breadth-first from an entry URL and converts to clean Markdown. The verb 'crawl' and resource 'multiple pages' are specific, and it distinguishes from siblings like 'scrape_url' (likely single page) and 'site_map' (sitemap generation).

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 comparison to sibling tools is provided. The description implies usage for bulk crawling with billing per page and no AI content, but lacks detailed guidance on when to choose crawl over extract or scrape_url.

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

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

No annotations provided, so description bears full burden. It describes output format (JSON with headers+rows for tables, text lists for selectors) but omits behaviors like error handling, authentication needs, or rate limits. Adequate but not comprehensive.

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

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

Two short sentences, no filler. Purpose is front-loaded, followed by key distinction. 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?

Given 100% schema coverage, no output schema, and 3 parameters, description clarifies output format and distinguishes from sibling. Could mention that it returns JSON of selected elements, but sufficient for agent to understand tool's role.

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%; all three parameters have descriptions. Description adds value for 'selectors' with example use case. For other parameters, description does not significantly extend schema info. Baseline 3 is appropriate.

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

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

Description clearly states the tool extracts structured elements from web pages (tables, links, images, headings, metadata, custom CSS selectors) and returns JSON. It uses a specific verb ('extract') and resource ('web page elements'), and distinguishes from sibling scrape_url by noting it does not return full page text.

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 contrasts with sibling scrape_url: '不返回整页正文，只返回指定结构', indicating when to use this tool over alternatives. Mentions custom selectors for precise extraction. Lacks explicit when-not 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?

With no annotations, the description carries the full burden. It clearly states the tool does static scraping, returns Markdown by default, and has an optional render mode for dynamic content. It also states it does not generate content. While it lacks details on rate limits or error handling, the core behavior is well disclosed.

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 two short paragraphs. The first sentence front-loads purpose and output. The second paragraph adds constraints and an option. Every sentence adds value, though it could be slightly more 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 4 parameters with full schema coverage, no output schema, and siblings listed, the description adequately covers the tool's usage and behavior. It explains constraints, parameters, and the main output format. It doesn't explain return format in detail but that is implied.

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

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

Schema description coverage is 100%, so baseline is 3. The description adds value by reinforcing the public URL requirement, explaining the render option for dynamic pages, and mentioning defaults (Markdown). This provides context beyond the schema 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 grabs a public webpage and returns clean Markdown. It specifically distinguishes from siblings like 'crawl' and 'extract' by emphasizing it only scrapes public webpages and does not generate content.

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 constraints (only public webpages, no internal/reserved addresses) and guidance on when to use the 'render' parameter for JS dynamic pages. However, it does not explicitly contrast with sibling tools or mention when to prefer 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?

With no annotations, the description carries the burden. It explains the discovery logic (robots.txt/sitemap priority, fallback), but lacks details about rate limits, authentication, following redirects, or the exact output format. It mentions saving credits, which adds some context.

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 (two sentences), front-loaded with the core purpose, and each sentence provides value. Slightly more structure (e.g., listing strategies) could improve clarity, but overall it's 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?

Given the tool's simplicity (2 params, no output schema), the description adequately covers the discovery strategy and usage pattern. It implies an array output ('URL list'), which is sufficient for an agent to understand and invoke the 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?

Schema coverage is 100%, so the baseline is 3. The description does not add additional meaning beyond what the input schema already provides for 'url' and 'max_urls'.

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 discovers a site's URL list using specific strategies (robots.txt, sitemap.xml, fallback). It distinguishes from siblings by positioning it as a preliminary step before precise scraping or crawling, saving credits.

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 advises using site_map first to select pages, then scrape_url or crawl. It provides clear context for when to use it, though it does not explicitly state when not to use it or mention alternative scenarios.

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