agent-web — URL to LLM-ready markdown: a polite, robots-respecting web page reader (free)

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

With no annotations, the description fully carries the burden of behavioral disclosure. It explicitly states it is read-only, polite, honors robots.txt, does not bypass anti-bot measures, and does not support JavaScript-rendered pages. This exceeds typical transparency expectations.

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, coherent paragraph of six sentences. It is mostly efficient but could be slightly more concise by breaking into bullet points. However, it front-loads the main purpose and follows with details, making it easy to parse.

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 an output schema, the description thoroughly explains the output format (title, description, word count, markdown) and how different inputs are processed (HTML vs plain text). It also covers limitations and behavioral constraints, making the tool's functionality fully understandable without additional documentation.

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 has 100% coverage with a single parameter 'url' described as 'absolute http(s) URL of a publicly reachable HTML page'. The description adds valuable nuance by explaining that plain text and raw Markdown files are also accepted and passed through, which is not evident from the schema alone. This compensates for any schema brevity.

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 fetches a publicly reachable URL and returns LLM-ready markdown with title, description, word count, and markdown content. It distinguishes from sibling tools like render_preview and render_screenshot by focusing on text extraction and conversion to markdown.

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 on when to use this tool: for publicly reachable URLs, especially HTML pages or plain text documents. It mentions limitations like no JavaScript-rendered pages and that it honors robots.txt. However, it does not explicitly name alternative tools for Js-heavy or paywalled content, though siblings like render_screenshot are 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?

With no annotations provided, the description carries full behavioral disclosure burden. It discloses that the tool is cheap/free, returns truncated content, and includes a truncation flag. It does not mention error behavior or rate limits, but for a simple preview tool this is largely sufficient.

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

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

Two sentences with no wasted words. It front-loads the 'like read_url' comparison, immediately establishes the output scope, and ends with a usage hint. Every sentence earns its place.

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 and low complexity (1 param), the description is quite complete: it specifies what the preview contains, when to use it, and indicates cost. Minor omission of error/edge-case behavior, but overall sufficient for the tool's simplicity.

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% (only one parameter, url, with a clear description). The description adds no additional meaning beyond what the schema provides for the parameter. 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 it returns a preview (page description + first ~600 characters of markdown with title, word count, truncation flag) of a URL. It explicitly distinguishes itself from sibling read_url by highlighting the reduced scope, which helps an agent differentiate between 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 says it is 'a cheap way to check a page's relevance before pulling the full text.' This provides clear guidance on when to use this tool (cheap relevance check) vs. alternatives like read_url (full text). It also mentions 'Free', offering a cost hint.

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 full burden. It discloses using a 'robots-respecting headless browser' and a 'soft-skip 503' behavior, but lacks details on return format, error handling, or payment flow. The behavioral traits are partially covered.

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

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

Two sentences, front-loaded with the essential action, no redundant information. Every sentence adds value, from payment hint to current limitation.

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 covers the paid nature, browser type, and a special behavior (503 skip), but does not explain what 'x402 payment instructions' are or how to handle them. Lacking output schema, the agent is left without return value info.

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% for the url parameter. The description does not add meaning beyond the schema's 'absolute http(s) URL to render to PDF'. Baseline score 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 clearly states it returns x402 payment instructions for a PDF render via a headless browser. It distinguishes from sibling tools like render_screenshot by specifying 'PDF render' and 'payment instructions', though the exact output (payment instructions vs. PDF) may cause confusion.

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 when a paid PDF render is needed ('PAID (x402)'), but does not explicitly state when to use versus alternatives like read_url or render_preview. No exclusions or prerequisites are provided.

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 clearly states the tool currently returns a 503, has robots and SSRF guards similar to read_url, and is a free discovery stub. This sufficiently discloses the current behavior given the absence of 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 two sentences long, front-loads the purpose ('Free discovery stub'), and every sentence provides essential information without redundancy or excess.

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 tool with one parameter and no output schema or annotations, the description adequately covers purpose, current behavior, and limitations. It does not address future behavior but that is acceptable for a stub.

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 provides 100% coverage for the single parameter 'url' with a basic description. The description adds meaningful context about URL constraints (SSRF guards, robots.txt handling) and the tool's purpose, enriching semantics beyond the schema alone.

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 identifies the tool as a 'free discovery stub' for rendering screenshots/PDFs, giving a clear general purpose. However, it does not differentiate this stub from the actual render tools (render_pdf, render_screenshot) in terms of when one should be used over the other.

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 use for testing the render pipeline without cost or triggering full rendering, but lacks explicit guidance on when to use this stub vs. the production render tools. No alternatives or exclusions are provided.

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?

Despite no annotations, the description discloses key behaviors: it is paid (x402), returns payment instructions (not the screenshot), uses a real browser that respects robots.txt, and currently soft-skips 503 errors. It does not detail response format or auth requirements beyond payment, leaving some gaps.

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: three sentences that front-load the core purpose (paid screenshot), followed by usage guidance and a current behavior note. Every sentence adds value without redundancy.

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 complexity (paid, payment flow, real browser, error handling), the description covers essential aspects. It mentions siblings and a prerequisite (publicly reachable URL). However, it lacks details on the payment process, expected response structure, and any rate limits, which would enhance completeness.

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

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

The input schema already provides clear descriptions for all 3 parameters (url, width, fullPage) with 100% coverage. The tool description adds only the condition that the URL must be 'publicly reachable,' which is not in the schema. This adds marginal 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 payment instructions for a PNG screenshot of a publicly reachable URL, using a real headless browser. It distinguishes itself from sibling tools like render_preview (free) and render_pdf by specifying the paid, screenshot-focused nature.

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 guidance to use render_preview (free) first, which is an alternative. However, it does not elaborate on when not to use this tool beyond suggesting the preview, nor does it mention prerequisites like URL accessibility (only implied).

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