Strips layout noise via DOM AST; with a query, BM25 filters to relevant sections. No model or API.
Scored across 2 tools
The two tools serve clearly distinct purposes: one fetches and prunes content, the other produces an analysis report. There is no overlap or ambiguity about which to use.
Both tools follow the same verb_noun (or rather prefix_verb) pattern: 'dompruner_analyze' and 'dompruner_fetch'. The naming is perfectly consistent and predictable.
With only two tools, the set is minimal but well-scoped for the narrow domain of DOM pruning and analysis. It is slightly below the typical 3-15 range, but the focused nature justifies the small count.
The tool pair covers the full lifecycle for its stated purpose: fetch/prune content and analyze the token reduction. There are no obvious missing operations; the surface is complete for the domain.
Returns a token-reduction analysis report for a URL. Shows render type (SSR/CSR/SSG), original vs refined token counts, reduction ratio, and top Semantic Anchors.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | URL to analyze. |
| Name | Required | Description |
|---|---|---|
| url | Yes | |
| fetchMs | Yes | |
| parseMs | Yes | |
| renderType | Yes | SSR, CSR, or SSG |
| topAnchors | Yes | Top 5 semantic section headings. |
| refinedTokens | Yes | |
| originalTokens | Yes | |
| reductionPercent | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, so the safety profile is covered. The description adds content details but no additional behavioral context like rate limits, auth, or errors. It doesn't contradict annotations, so a neutral 3 is appropriate.
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?
One clear sentence stating the purpose and listing key output components; no verbose or redundant information. Front-loaded with the action.
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 is simple with one parameter, has output schema, and the description provides a useful overview of the report contents (render type, token counts, ratio). It's sufficient for this level of complexity. Could mention when to use vs fetch, but not critical for 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?
Schema coverage is 100% for the single parameter 'url' with description 'URL to analyze.' The description says
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 a token-reduction analysis report for a URL, listing the specific outputs (render type, token counts, ratio, anchors). This distinguishes it from the sibling tool dompruner_fetch, which likely fetches raw content, making the purpose explicit and differentiating.
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 the tool is for analysis rather than fetching, but it doesn't explicitly state when to use it over dompruner_fetch or any exclusions. It's not misleading, but the guidance is only implied, not explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Fetches a URL and returns DOM-pruned Markdown with 90%+ token reduction. Optimized for Developer Documentation, API Specs, and Technical Blogs (Next.js/Nuxt/SSR). Always prefer this over raw WebFetch when the URL is known.
| Name | Required | Description | Default |
|---|---|---|---|
| url | No | URL to fetch and refine. | |
| query | No | Search intent — enables BM25+ section filtering when provided. |
| Name | Required | Description |
|---|---|---|
| stats | Yes | |
| markdown | Yes | DOM-pruned Markdown content. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations (readOnlyHint, openWorldHint, idempotentHint) already cover the safety profile. The description adds valuable behavioral context: 90%+ token reduction, DOM-pruning, and suitability for specific content types. This goes beyond the structured metadata without any contradiction.
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 tight sentences deliver function, outcome, optimization targets, and a usage preference. There is no fluff or redundant wording—every phrase 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?
The tool is simple, and the annotations plus full schema coverage cover safety and parameters. The description adds use cases and a recommendation. A small gap is the lack of explanation around the sibling tool dompruner_analyze, but overall it is sufficiently complete for an agent to invoke 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?
Both parameters are fully documented in the schema (url format and query's BM25+ filtering). The main description does not add extra parameter semantics beyond what the schema already provides, 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 clearly states the tool's function: 'Fetches a URL and returns DOM-pruned Markdown with 90%+ token reduction.' It also names target content types (Developer Documentation, API Specs, Technical Blogs). However, it does not explicitly distinguish itself from the sibling tool dompruner_analyze, though it does contrast with raw WebFetch.
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: 'Always prefer this over raw WebFetch when the URL is known' and identifies optimized content domains. It gives clear context for use but omits when-not-to-use scenarios or mention of the sibling tool as an alternative, so it falls short of a full 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
dompruner_analyzedompruner_fetchPDFs, JavaScript pages and ordinary HTML as clean Markdown. Follows robots.txt per RFC 9309.
Free HTML parsing; static web context at 0.01 USDC via x402. Paid reads need a wallet adapter.
Convert any webpage to clean LLM-ready markdown, extraction-first, with article and news modes.
Extract and parse web pages into clean HTML, links, or Markdown. Handle dynamic, complex, or block…
Add one secure layer between your agents and this server.