Web Extract MCP Server

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

With no annotations, the description carries the full behavioral burden. It usefully discloses the no-account requirement, inline wallet payment model, and 402 flow, but it does not clearly state whether calling this tool itself is free/read-only or whether it can initiate payment, leaving a meaningful side-effect ambiguity despite the tool's zero-parameter nature.

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 compact and front-loads the main purpose, with the layer and price details following immediately. It is dense but mostly earns its length; a small amount of jargon reduces clarity slightly.

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, no-output-schema informational tool, the description adequately lists what is returned: metered layers, exact prices, pay-to address, and 402 flow explanation. The main remaining gap is explicit confirmation that the call itself does not transact and the expected return format.

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 there are no parameter semantics to explain and the baseline is 4. The description appropriately focuses on returned information rather than parameter behavior.

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 resource: it returns the paid x402 rail details, including metered depth layers, exact USDC/Base prices, pay-to address, and 402 flow. It is clear what the tool provides, though the phrase "Return the paid x402 rail" is somewhat jargon-heavy and the tool is not explicitly differentiated from its 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?

Usage context is implied by "No account; an x402-aware client pays inline from the agent's wallet," which tells the agent this is for discovering premium payment details. However, there is no explicit when-to-use guidance, no exclusions, and no reference to alternatives or prerequisites beyond the payment client requirement.

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 and does well: it discloses that the call is keyless (no auth), free, capped at 20 URLs, and sourced from robots.txt with a /sitemap.xml fallback, plus the lastmod payload. It doesn't cover failure behavior for invalid/unreachable domains or any rate limiting, which are the remaining 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?

Two sentences, both dense with decision-relevant facts, and the free-tier capability and limits are front-loaded before the paid alternative. No filler.

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?

Absent an output schema, the description compensates by stating the return shape (up to 20 URLs with lastmod) and the sitemap discovery sources, which is what an agent needs to call it correctly. Error/empty-result behavior is the only unaddressed piece.

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 'site' description already covers the domain/URL/direct-.xml forms; the description adds no syntax or format guidance beyond that. 'contains' is only referenced in the context of the paid tool, so the free tool's own filter semantics get no extra explanation. 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?

States a specific verb and resource ('discover a domain's sitemaps', 'return up to 20 page URLs with lastmod') and explicitly positions itself against the paid /web/sitemap alternative. An agent can distinguish it from get_premium_access without opening either schema.

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 frames itself as the free/keyless option versus the paid '/web/sitemap ($0.003)' that returns 5000 URLs across 10 files, and routes the agent to 'get_premium_access' when the larger result or substring filtering is needed. The selection condition between the two is spelled out rather than inferred.

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 and delivers: no auth required (keyless), no cost, SSRF-guarded safety posture, one-URL-at-a-time throughput limit, and the non-obvious capability that JS/SPA pages are rendered without a browser. That is behavioral context an agent cannot infer from the schema.

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?

Front-loaded with the value proposition ("Free keyless live web read") followed by output shape, safety, and the paid upgrade path. Dense but every clause carries information; nothing is redundant with the schema.

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?

There is no output schema, and the description compensates by naming the returned fields (title, metadata, main text, injection flag). It also covers the auth, cost, and safety dimensions that annotations would normally supply, so nothing essential is missing for a single-parameter read tool.

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

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

One parameter at 100% schema coverage, so the schema already defines it as a public http(s) URL. The description adds only the practical constraint that it must be public and that only one is accepted per call — useful but marginal over 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?

Names a specific verb (fetch) and resource (ONE public URL) and enumerates the return payload: title, metadata, boilerplate-stripped main text, plus an injection-screen flag. It explicitly contrasts itself with the paid /web/extract, so an agent can distinguish it from siblings without opening any schema.

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?

States the selection conditions directly: free, keyless, single URL ("ONE public URL now"). It then names the alternative and the exact conditions that route to it (Markdown, full link graph, 10-URL batches) and gives the follow-up call (get_premium_access) with pricing.

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