redreplier

Edit Keyword

edit_keyword

Destructive

Replace a keyword's text in place, preserving its ID and paid slot. Fix a grader-suspended keyword or reword without adding a duplicate variant.

Instructions

Change a keyword's text in place, keeping its ID and any paid slot. Edits are unlimited on every plan (keyword_change_usage reports limit -1). The new value is re-graded for noise; an ACTIVE keyword stays ACTIVE, while a PENDING, DISABLED, or SUSPENDED one goes ACTIVE if the plan has a free slot and PENDING otherwise. Use this to fix a SUSPENDED keyword the grader rejected, or to reword instead of adding a variant with add_keywords. A case-only change is a no-op; a value already on the website returns 400.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`value`	Yes	New keyword text; trimmed and lowercased, must not duplicate another keyword on the same website
`keywordId`	Yes	Keyword ID (UUID)

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	No	The updated keyword with its new value and resulting status (ACTIVE or PENDING).

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv0.1.1Sep 7, 2026

changedInput schema / properties / value / description

Previous value: -"New keyword text"New value: +"New keyword text; trimmed and lowercased, must not duplicate another keyword on the same website"

changedOutput schema / properties / result / description

Previous value: -"The updated keyword with its new value and status."New value: +"The updated keyword with its new value and resulting status (ACTIVE or PENDING)."

First observedv0.1.0Sep 7, 2026

TDQS

A4.9/5.0

Behavior5/5

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

The description goes beyond annotations (destructiveHint:true, readOnlyHint:false) by detailing exact behaviors: unlimited edits, re-grading for noise, status transitions (ACTIVE stays ACTIVE, others go ACTIVE if slot free else PENDING), and duplicate handling. This level of detail is highly transparent.

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 dense but well-organized, covering multiple important aspects in three sentences. It is slightly long but every sentence adds critical information, so it remains efficient.

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?

Given the tool's complexity (status transitions, billing implications, uniqueness checks), the description covers all key behaviors the agent needs to know. It explains the impact on paid slots, re-grading, and error conditions, making it fully sufficient for correct invocation.

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?

Although the schema already covers keywordId and value with descriptions, the tool description adds meaningful context: 'keeping its ID' clarifies the ID is preserved, 'case-only change is a no-op' explains value normalization, and 'value already on the website returns 400' warns of uniqueness constraints.

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 clearly states the tool's purpose: 'Change a keyword's text in place, keeping its ID and any paid slot.' It distinguishes itself from add_keywords by explicitly noting 'reword instead of adding a variant with add_keywords.'

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 provides explicit when-to-use guidance: 'Use this to fix a SUSPENDED keyword the grader rejected, or to reword instead of adding a variant with add_keywords.' It also clarifies edge cases like case-only changes being no-ops and duplicate values returning 400.

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