Lekta

Audit a page the way AI answer engines read it

lekta_audit

Read-only

Fetches ONE page exactly the way answer engines do (plain GET as LektaBot + a Chromium render pass) and grades it A+ to F across four layers: Access (robots.txt permissions for ~17 AI crawler tokens), Indexability (how much content exists without JavaScript), Answerability (is there a quotable answer) and Recency (is the page dated). Returns a readable verdict: grade, the issues ranked by point impact, and the complete fix for each. USE THIS when you need the current state of a page or after deploying fixes. DO NOT use it for machine parsing (use lekta_report for JSON), for planning without a new measurement (lekta_fix_plan), or to compare two runs (lekta_diff). COST AND BEHAVIOUR: takes 5-30 s (75 s hard limit), honors robots.txt, consumes one fresh-audit slot from the daily MCP quota; a repeat call within 15 minutes returns the cached measurement for free. The audited site is never modified.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`url`	Yes	Absolute http(s) URL of ONE page, e.g. https://example.com/pricing. Not a domain list, not a sitemap — audit a representative content page, not only the homepage.

TDQS

A4.7/5.0

Behavior5/5

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

Annotations already provide readOnlyHint=true and destructiveHint=false, but the description adds substantial behavior: plain GET as LektaBot plus a Chromium render pass, honors robots.txt, consumes a daily fresh-audit slot, caches for 15 minutes, takes 5-30 seconds, and 'The audited site is never modified.' This goes well beyond the structured hints and does not contradict them.

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?

The description is front-loaded with the core verb, scope, and grading layers, then organized into usage, exclusions, and cost/behavior sections. Despite its length, every sentence contributes distinct, actionable information such as quota, caching, timing, and alternative routing.

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

Completeness5/5

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

With no output schema, the description still explains the return shape: 'grade, the issues ranked by point impact, and the complete fix for each.' It also covers performance limits, quota behavior, caching, robots.txt handling, and non-modification, so an agent has everything needed to invoke it correctly.

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

Parameters3/5

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

The single url parameter already has 100% schema description coverage, including 'Absolute http(s) URL of ONE page' and 'Not a domain list, not a sitemap.' The tool description reinforces the one-page scope and adds fetch-mode context, but it does not add new parameter format or constraint details beyond what the schema already provides.

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?

The description states a specific action and resource: 'Fetches ONE page exactly the way answer engines do' and grades it A+ to F across four named layers. It also clearly distinguishes itself from siblings by naming when to use it versus the alternatives.

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

Usage Guidelines5/5

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

The description contains explicit guidance: 'USE THIS when you need the current state of a page or after deploying fixes' and 'DO NOT use it for machine parsing... planning without a new measurement... or to compare two runs.' It names the correct alternative tool for each excluded case, leaving no ambiguity.

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

All Lekta tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.5/5.0

Disambiguation4/5

Each tool has a clear role: audit and report are the same measurement with different output formats, but the descriptions explicitly separate human-readable verdicts from machine-readable JSON. Diff and fix plan operate on stored audits, and my_sites lists account sites, so there is only minor potential confusion between audit and report.

Naming Consistency3/5

All tools share the lekta_ prefix and use snake_case, but the second part mixes verbs (audit), nouns (diff, report), and multi-word phrases (fix_plan, my_sites). The naming is readable and predictable enough, but it does not follow a single consistent verb_noun convention.

Tool Count5/5

Five tools is well-scoped for a focused audit-and-fix workflow: measure, get details, plan fixes, compare progress, and list sites. No tool feels redundant, and the count is comfortably within the ideal range.

Completeness4/5

The tool surface covers the core lifecycle of auditing a page, retrieving structured results, planning fixes, and verifying improvement via diffs. Minor gaps exist, such as no tool to manage scheduled rechecks or delete sites, but these do not block the primary workflow.

Resources

Need Help?