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 provided, the description carries full burden and excels: it details the read-only GET behavior, honoring robots.txt, honest identification, no bypassing of anti-bot measures or paywalls, and the free nature. It also explains how different content types are processed (HTML via extraction, markdown/plain text verbatim).

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 well-structured and front-loaded with the key output 'LLM-ready markdown'. Every sentence adds useful information without unnecessary fluff. While slightly lengthy, it remains clear and focused.

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 adequately outlines the return components (title, description, word count, markdown). It covers input constraints and behavioral nuances. For a simple one-parameter tool, it is comprehensive, though it could specify the exact output format more explicitly.

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 for the single 'url' parameter with a description. The description adds value beyond the schema by explaining the behavior for different URL types (HTML vs markdown/plain text) and reiterating that URLs must be publicly reachable. This enriches the parameter understanding.

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 single publicly reachable URL and returns clean, LLM-ready markdown including title, page description, word count, and markdown content. It distinguishes from siblings by specifying different handling for HTML vs plain text, and the sibling names imply different scopes (preview, render).

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 the tool (fetching public URLs) and explicitly states a limitation (no JavaScript-rendered pages). It does not explicitly compare with siblings but implies use cases by mentioning what it handles (HTML, markdown, plain text) versus what it does not (JS-rendered).

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?

Describes return content and cheapness but doesn't explicitly state it's non-destructive or require auth. 'Free' is ambiguous (cost vs. free of restrictions). With no annotations, more clarity on side effects would help.

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, no filler. Front-loaded with comparison to sibling tool. 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?

For a simple tool with one param and no output schema, the description is mostly complete: explains what it returns, why use it, and how it differs from sibling. Could mention error handling but not critical.

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 the single parameter with a clear description. The tool description adds context about usage but does not extend parameter meaning beyond schema, 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?

Clearly states it returns a preview (description + first ~600 chars of markdown) of a URL, distinguishing from read_url by noting it's cheaper and for checking relevance.

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 says it's a 'cheap way to check a page's relevance before pulling the full text', implying use for previews. No explicit exclusions or alternatives beyond the sibling mention.

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 mentions it uses a 'real, robots-respecting headless browser' and 'soft-skips 503', adding useful behaviors. No annotations exist, so transparency is adequate but not exhaustive; missing details like rate limits or payment flow.

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 key info (PAID, x402). The second sentence is somewhat technical but still concise. No 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 no output schema and one parameter, the description covers inputs and core behavior. However, it lacks details on the return format of payment instructions and how it relates to sibling rendering 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 already covers the 'url' parameter well (100% coverage). The description adds the 'publicly reachable' constraint, adding value beyond schema.

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

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

Description states it returns 'x402 payment instructions for a PDF render', which is specific and differentiates from sibling tools like render_screenshot or read_url. However, it lacks explicit comparison to siblings.

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 on when to use this tool vs. alternatives like render_preview or read_url, nor any indication of prerequisites beyond a publicly reachable 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?

The description discloses current behavior (returns 503), guards (robots/SSRF), and that it is a stub. However, it lacks clarity on future behavior and does not explicitly declare side effects or safety, which annotations would typically cover.

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, no wasted words. Front-loads the core purpose and then adds necessary context about guards and current status.

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 stub tool, the description provides essential context: purpose, current limitation, and similarity to read_url. Lacks guidance on siblings and future behavior, but is adequate given the tool's temporary nature.

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 a complete description for the single parameter 'url' (publicly reachable URL). The description adds no further semantic 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 it is a 'Free discovery stub for the screenshot/PDF render lane,' indicating its role as a placeholder to test the render pipeline. It also notes similarity to read_url, but the verb 'discover' is implied rather than explicit.

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 siblings like render_pdf or render_screenshot. It mentions it returns 503 currently but doesn't advise against relying on it for actual rendering.

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: paid (x402), uses real headless browser, respects robots.txt, returns payment instructions (not the image), and soft-skips 503 until Cloudflare provisioning.

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 concise sentences front-load critical information (paid, use preview first) and efficiently convey the tool's purpose and limitations.

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 paid tool returning instructions, the description covers purpose, prerequisites, and current limitations. Without an output schema, the return format is implied but not detailed, which is acceptable.

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% and each parameter has a description. The tool description adds no additional parameter meaning beyond what the schema provides, so 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?

Clearly states it returns payment instructions for a screenshot via a headless browser, distinguishing from render_preview (free). The verb 'returns' and resource 'PNG screenshot' are specific.

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 advises using render_preview first, and mentions the paid nature and current soft-skip for 503. However, does not explicitly state when not to use this tool beyond suggesting preview first.

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