Citation Intelligence MCP

audit_llms_txt

Read-onlyIdempotent

Generate an llms.txt file from a sitemap: parse sitemap.xml and nested indexes, group URLs by top-level path, and output a Markdown document with sectioned link lists.

Instructions

Generate an llms.txt file (https://llmstxt.org spec) from a sitemap. Parses sitemap.xml + nested indexes, groups URLs by top-level path, and emits a Markdown document with H1+description+sectioned link lists. Set fetch_titles=true to pull per URL (slower, richer output).

Input Schema

TableJSON Schema

Name	Required	Description
`limit`	No	Max URLs to include. Truncated after sitemap parse, before title fetch.
`site_title`	Yes	Site title - top H1 in the generated llms.txt file.
`sitemap_url`	Yes	URL of sitemap.xml (or sitemap index). Nested sitemaps are followed.
`fetch_titles`	No	If true, fetch each URL to extract <title> for richer links. Slower (one HEAD-ish GET per URL). Default false uses the URL path as the link text.
`site_description`	No	One-paragraph site description placed under the H1. Optional but strongly recommended.

Output Schema

TableJSON Schema

Name	Required	Description
`note`	No
`content`	Yes	Generated llms.txt file content; save to /llms.txt at site root.
`sections`	Yes	Number of top-level sections in the generated file.
`fetched_at`	Yes	UTC ISO-8601 timestamp.
`sitemap_url`	Yes	Sitemap URL that was processed.
`urls_included`	Yes	URLs included after applying the limit.
`titles_fetched`	Yes	Number of pages fetched to extract <title>.
`total_urls_in_sitemap`	Yes	Total URLs found in the sitemap.

Schema Changelog

Changes observed during successful MCP inspections.

Addedv0.1.2Oct 2, 2026

TDQS

A4/5.0

Behavior3/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld). The description adds useful procedural context: sitemap parsing, nested index following, and the slower/richer tradeoff of fetch_titles. However it doesn't state limits, pagination, or failure modes beyond what the schema already says.

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

Conciseness5/5

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

Two tight sentences, front-loading the artifact and spec, then the pipeline, then the key parameter tradeoff. No filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Annotations carry safety, an output schema exists, and schema descriptions are complete. The description fills the remaining gaps (pipeline behavior, fetch_titles tradeoff). Minor gap: no mention of rate limits or failure behavior when the sitemap is unreachable.

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

Parameters4/5

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

Schema coverage is 100%, so baseline is 3. The description adds meaning by explaining the fetch_titles tradeoff and the output structure (H1+description+sectioned links), which helps the agent reason about parameter selection beyond the schema's per-parameter notes.

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

Purpose5/5

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

States a specific verb (generate) and artifact (llms.txt file) and names the spec URL. Distinct from every sibling (audit_*, citations_*, competitors_*, etc.), none of which produce an llms.txt.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains what it does and hints at the fetch_titles tradeoff, but provides no explicit when-to-use vs when-not-to-use guidance or alternative selection against siblings.

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