Skip to main content
Glama

John's Essentials

by com.johnsessentials
OverviewDiscussionsAdmin

analyze_grammar_check

Read-only

Grammar Checker — Hybrid LanguageTool + Grok grammar checker with rule citations, style-guide awareness (APA/MLA/Chicago/AP/IEEE), dialect enforcement (US/UK/CA/AU), and per-issue severity. [category: analyze]

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNoKeep my voice leaves your phrasing alone; Strict also flags casual or loose wording.tone-preserving
textYesThe text to check (max 50,000 characters).
styleNoStyle-guide conventions to enforce (e.g. Oxford comma for APA/MLA/IEEE/Chicago, dropped for AP).none
dialectNoEnglish dialect for spelling and grammar rules.en-US
include_llmNoAdds a second pass that catches wording and context problems the rule checker cannot see. Turn off for rule-based results only, which is faster.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / text / x-ui
      Added value: +{
+  "multiline": true
+}
  2. Changed9 schema fields changed
    • addedInput schema / properties / dialect / title
      Added value: +"English spelling"
    • addedInput schema / properties / dialect / x-ui
      Added value: +{
+  "labels": {
+    "auto": "Detect automatically",
+    "en-AU": "Australian English",
+    "en-CA": "Canadian English",
+    "en-GB": "British English",
+    "en-US": "American English"
+  }
+}
    • changedInput schema / properties / include_llm / description
      Previous value: -"Run the Grok stage for context-dependent issues LanguageTool misses. Set false for rule-only output."New value: +"Adds a second pass that catches wording and context problems the rule checker cannot see. Turn off for rule-based results only, which is faster."
    • addedInput schema / properties / include_llm / title
      Added value: +"Deeper AI check"
    • changedInput schema / properties / mode / description
      Previous value: -"strict = flag any casual phrasing; tone-preserving = preserve the author's voice."New value: +"Keep my voice leaves your phrasing alone; Strict also flags casual or loose wording."
    • addedInput schema / properties / mode / title
      Added value: +"How picky should it be"
    • addedInput schema / properties / mode / x-show-when
      Added value: +{
+  "include_llm": [
+    true
+  ]
+}
    • addedInput schema / properties / style / title
      Added value: +"Style guide"
    • addedInput schema / properties / style / x-ui
      Added value: +{
+  "labels": {
+    "ap": "AP",
+    "apa": "APA",
+    "chicago": "Chicago",
+    "ieee": "IEEE",
+    "mla": "MLA",
+    "none": "No style guide"
+  }
+}
  3. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already mark the tool read-only, so the description adds value by disclosing the hybrid engine, rule citations, style-guide awareness, dialect enforcement, and per-issue severity. This gives an agent useful behavioral expectations beyond the annotation flags, though it does not specify output structure.

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

Conciseness4/5

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

The description is a single dense sentence that front-loads the tool's identity and then lists distinguishing capabilities. The category tag at the end is redundant but not harmful. It compresses a lot of information without excessive wordiness.

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?

With five parameters, full schema documentation, and no output schema, the description provides a solid behavioral overview including citations, severity, style, and dialect. It does not describe the exact return shape, but the feature list sufficiently orients an agent to what the tool produces.

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?

Schema description coverage is 100%, so the input schema already documents text, mode, style, dialect, and include_llm thoroughly. The description's style and dialect mentions mirror schema enums rather than adding new parameter-level meaning; the only slight extra is the Grok reference hinting at the LLM pass.

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

Purpose4/5

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

The description clearly identifies the tool as a grammar checker with a hybrid LanguageTool + Grok engine and lists concrete capabilities (style guides, dialect enforcement, per-issue severity). This is sufficient to distinguish it from sibling analyze_* tools, though it relies on the title phrase rather than an explicit verb phrase like 'check grammar in text.'

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?

Usage context is implied by the name and category: use this tool when the user wants grammar checking with style and dialect support. However, the description does not state when to prefer it over alternatives or what it is not for, and no sibling alternative is named.

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

All John's Essentials toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources