Skip to main content
Glama

Check a draft

check_content

Run the gates on a local draft before the PR: fabrication (numbers with no source), unsupported claims, disparagement of other products, duplication, placeholders left in, banned machine-sounding words, dashes, answer-first opening, headings, length and links. Pass the facts content_brief returned. Free.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "type": "<type>",
      "markdown": "<markdown>"
    },
    "name": "check_content"
  }
}

Input Schema

NameRequiredDescriptionDefault
typeYes
factsNo
titleNo
markdownYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior4/5

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

Adds information beyond the annotations: it discloses that the tool is 'Free' (no cost) and that it works on a local draft rather than publishing anything, which tempers the openWorldHint. The gate list also describes what the checks cover. It does not explain what a failing gate does or how results come back, and the readOnlyHint=false is slightly surprising for a tool framed purely as a check.

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?

Front-loaded with the action and framed with the workflow position ('before the PR'). The long enumeration of gates is dense but each item is informative; the trailing 'Free.' is a worthwhile single word.

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

Completeness3/5

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

With no output schema, four parameters at 0% schema description coverage, and no annotation detail, the description leaves gaps: it never says whether the return is a pass/fail verdict, a list of violations with locations, or a rewritten draft, nor what the agent should do with a failure. It is adequate to call the tool but not to act on its results.

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 0%, so the description must compensate, and it partially does: it clarifies that 'facts' comes from content_brief and that the target is a local draft in markdown. However, the 'type' enum (answer_page/comparison/alternatives/glossary_term/article) and 'title' are never explained, and there is no hint that 'type' changes which gates apply.

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 and resource ('run the gates on a local draft') and then enumerates the concrete gate categories (fabrication, unsupported claims, disparagement, duplication, placeholders, banned words, dashes, answer-first opening, headings, length, links). This is clearly a pre-publish validation tool distinct from generation siblings like content_brief or grow_answer.

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

Usage Guidelines4/5

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

Gives clear timing ('before the PR') and an explicit input dependency ('Pass the facts content_brief returned'), which tells the agent the correct call order. It does not distinguish itself from adjacent checks such as landing_check, funnel_check, or ideas_check, so there is no when-not-to-use guidance.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources