reright

keep_original

Idempotent

Call this only when a rewrite changed a fact, a name, a number, a date, a yes or no or a promise, or reversed the meaning. Different wording, tone, sentence order or style is not a reason: the user wants the rewrite, and your own text sounds like AI. Removed padding is not a changed fact either: pleasantries, empty offers, frames such as "It's worth noting that" and repeats that reright took out (removed_padding) were removed on purpose, and a call that quotes them is refused. Pass the id, a category, the exact phrase from your text as original and the phrase in final_text that replaced it as rewritten, each copied word for word, at most 140 characters. It returns your own text as final_text; use that exactly. When the user's setting is "Only when unsure", it returns status pending with a review_url instead: the user decides between the two versions, so give the user the link, ask them to open it and approve or edit, and call rewrite_result with the id until it is not pending. It works only for a rewrite nobody checked. When the user checked or edited the text, the user's version stands.

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": {
      "id": "<id>"
    },
    "name": "keep_original"
  }
}

Input Schema

Name	Required	Description
`id`	Yes	the id returned by rewrite
`reason`	No	not used; send category, original and rewritten
`category`	No	required: what the rewrite changed, one of fact, name, number, date, negation (a yes or no turned around), promise, other
`original`	No	required: the exact phrase from your text that the rewrite changed, copied word for word, at most 140 characters
`rewritten`	No	required: the exact phrase in final_text that replaced it, copied word for word, at most 140 characters

Output Schema

Name	Required	Description	Default
`id`	Yes
`run`	No
`note`	No
`agent`	No
`reason`	No
`status`	Yes
`rewritten`	Yes
`final_text`	No
`review_url`	No
`instruction`	Yes
`upgrade_url`	No
`removed_padding`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 8, 2026

addedOutput schema / properties / removed_padding

Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "type": [
+    "null",
+    "array"
+  ]
+}

First observedNov 8, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Beyond the annotations, it discloses refusal behavior (quotes of removed_padding are refused), the pending/review_url flow under the 'Only when unsure' setting, and the requirement to poll rewrite_result until no longer pending. That is substantive behavior an agent could not infer. It does not explicitly restate the idempotent or non-destructive profile, but the annotations already carry those.

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 exclusion rules are front-loaded, which is the right ordering for a guardrail tool, and the call mechanics and return behavior follow. It is dense and slightly long, and contains rough phrasing and a typo ('reright'), but nearly every clause carries an actionable constraint.

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 guardrail tool with five parameters, an output schema and rich annotations, the description covers entry conditions, exclusions, refusal behavior, the review_url branch, and follow-up polling. Nothing an agent needs to call it correctly is missing.

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 the baseline is 3, but the description adds real meaning: it asserts that category, original and rewritten are required in practice even though the schema's required list names only id, and it emphasizes word-for-word copying with a 140-character cap. It also steers the agent away from the unused 'reason' parameter.

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 makes clear this tool overrides a rewrite with the user's own original text, and names the resource ('your own text as final_text'). It is specific enough to distinguish from rewrite and rewrite_result, though the core purpose is stated late rather than in an opening verb+resource sentence.

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?

It gives explicit when-to-call conditions (fact, name, number, date, yes/no, promise, reversed meaning) and explicit when-not conditions (wording, tone, order, style, removed padding). It also carves out a boundary against the sibling by noting it works only for an unchecked rewrite and that a user-checked version stands.

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

All reright tools Inspect

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

Need Help?