Nero Reviews: verified job reviews for trades

Dispute an unfair or unlawful review

dispute_review

The dispute desk. Used when the trade says a review is unfair, untrue, from someone who was not their customer, blackmail ("refund me or I leave 1 star"), or contains private details, abuse or something legally wrong. It settles the dispute straight away from fixed rules (no person reads it, except legal notices) and returns verdict ("review_stays" or "sent_to_nero"), why, what_you_can_do and usually an example_reply the trade can adapt for their public reply. A genuine customer's opinion is never removed, because hiding real negative reviews is banned by UK law (DMCC Act 2024); private details and swearing are already removed by machine before any review is published. Reasons: not_true, customer_was_to_blame (for example they were out, or changed the job), asked_for_money_or_threatened, not_my_customer, not_about_this_job, personal_data, abusive_language, legal_notice (a solicitor's letter or court order; put the details in note). The review stays visible and counting whatever the verdict.

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": {
      "trade_key": "<trade_key>",
      "review_id": "<review_id>",
      "reason": "<reason>"
    },
    "name": "dispute_review"
  }
}

Input Schema

Name	Required	Description
`note`	No	Optional. The trade's side in a sentence or two, or for legal_notice who sent it and what it says.
`reason`	Yes
`review_id`	Yes	review_id from my_score or list_reviews.
`trade_key`	Yes	The trade_key that register_trade returned for this business (starts with nrk_).

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 12, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations declare readOnlyHint=false, destructiveHint=false and idempotentHint=false but say nothing about automation, human review, or outcomes. The description fills that gap: it settles immediately from fixed rules, no person reads it except legal notices, and the review stays visible and counting regardless of verdict. The one residual gap is that it never says whether a dispute can be re-filed or what happens to the review's score during processing.

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 purpose and triggering conditions, then mechanism, then the reason list, which is the right order for an agent scanning it. There is mild redundancy between 'A genuine customer's opinion is never removed' and 'The review stays visible and counting whatever the verdict', two sentences making nearly the same point.

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 no output schema, the description carries the return-value burden and does so by naming verdict values, the why/what_you_can_do fields, and the example_reply. Combined with the enum explanations and the stated automation behavior, an agent has enough to call it and interpret the result; only edge cases like duplicate disputes remain unaddressed.

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 75%, and the description compensates by unpacking the reason enum, which the schema lists without per-value explanations: customer_was_to_blame gets concrete examples ('they were out, or changed the job'), legal_notice gets routing advice ('put the details in note'), and blackmail is glossed as asked_for_money_or_threatened. trade_key and review_id are left to the schema, which already documents them well.

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 names a specific action and resource (dispute a review) and states the mechanism (fixed-rule adjudication) and the output shape (verdict, why, what_you_can_do, example_reply). The title plus 'The dispute desk' immediately separates it from sibling write tools like reply_to_review.

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?

It gives concrete triggering conditions: unfair, untrue, non-customer, blackmail, private details, abuse, or legally wrong, and maps these onto the reason enum. It also carves out an exception (legal notices are the one thing a person reads). It does not explicitly name an alternative tool such as reply_to_review for the case where the trade just wants to respond publicly, so routing is implied rather than stated.

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

All Nero Reviews: verified job reviews for trades 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.