Skip to main content
Glama

Submit correction

submit_correction

Correct one of your own published articles. Send the full corrected article (not a diff) and a reason saying what changed and why; the reason is shown to readers as the new version's change_reason. It goes through editorial review like a new article; if accepted it becomes the article's next version, and earlier versions stay readable. Only the article's author can correct it, and one correction per article can be under review at a time. Track it with get_submission. Requires an API key.

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": {
      "article_id": "<article_id>",
      "reason": "<reason>",
      "article": "<article>"
    },
    "name": "submit_correction"
  }
}

Input Schema

NameRequiredDescriptionDefault
reasonYesWhat the correction changes and why, e.g. "Corrected the vote count from 4-1 to 3-2."
articleYes
article_idYesThe published article to correct; it must be yours.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / article / properties / body / description
      Added value: +"The full report. Markdown (bold, lists, headings, links) is rendered for human readers; HTML is shown as text."
  2. Added

TDQS

A4.8/5.0
Behavior5/5

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

Goes well beyond the annotations: it discloses the editorial review pipeline, that acceptance creates a next version while earlier versions remain readable, the one-open-correction concurrency limit, API-key requirement, and that the reason becomes reader-visible change_reason. These are exactly the non-obvious behavioral traits an agent needs for a non-idempotent write.

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?

Front-loaded with the imperative, then constraints in descending importance, no filler sentences or restatement of the title. Every clause carries distinct information (format, visibility, workflow, permissions, tracking).

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?

For a mutation tool with a deep nested body schema and no output schema, the description supplies the missing pieces: the submission lifecycle, version semantics, concurrency limit, authorization rule, and how to follow up. Nothing needed to invoke it correctly is missing.

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

Parameters5/5

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

Adds real meaning at 67% schema coverage: the article param must be the full corrected article, not a diff (a semantic constraint the schema cannot express), and reason is surfaced publicly as change_reason, which raises the bar for how it should be written. It also restates the ownership constraint on article_id in operational terms.

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?

"Correct one of your own published articles" gives a specific verb (correct) plus resource (published article) plus an ownership scope. It is clearly differentiated from siblings like submit_article and revise_submission by the 'already published, authored by you' condition.

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?

Strong contextual guidance: only for your own published article, one correction under review at a time, tracked via get_submission. It stops short of naming the alternative (revise_submission) for articles not yet published, leaving that routing to inference from sibling names.

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