Squish

Apply ai visibility fixes

apply_ai_visibility_fixes

Destructive

Applies AI Visibility fixes to one of the customer's OWN hosted WordPress sites — adds business structured data (schema), a meta description, and an FAQ page. Two-step usage: (1) call with confirm:false to PREVIEW — returns exactly which fixes would be applied and anything still needing the customer's business details; describe that and ask them to confirm. (2) ONLY after the user clearly says yes, call again with confirm:true to apply. Never pass confirm:true without an explicit yes in the user's most recent message. The domain must be one of the user's own Squish-hosted WordPress sites. Every change is made behind a pre-edit restore point and a bad apply is rolled back automatically — nothing is left half-applied. HONESTY: this makes the site readable and understood by AI; it never promises an engine will recommend or cite the business.

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": {
      "domain": "<domain>"
    },
    "name": "apply_ai_visibility_fixes"
  }
}

Input Schema

Name	Required	Description	Default
`domain`	Yes	The customer's hosted WordPress site to fix (their domain).
`confirm`	No	false (default) previews the fixes. true applies them — ONLY after the user explicitly agreed.

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 8, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Beyond the annotations, the description explains the preview behavior, the need for explicit user confirmation, the pre-edit restore point, automatic rollback on a bad apply, and the honesty limitation that it does not promise AI engines will recommend or cite the business. These details materially improve behavioral transparency for a destructive mutation tool.

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?

The description is front-loaded, well structured, and every sentence serves a purpose: the action, the two-step confirmation flow, safety behavior, domain restriction, and honesty caveat. Despite its length, it contains no obvious filler.

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?

It is complete enough for a complex mutation tool: it covers preview versus apply, confirmation requirements, rollback safety, and domain eligibility. The only minor gap is that it does not explain the result shape, though no output schema exists and the preview description partially covers what the user will see.

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 coverage is 100%, so both parameters are already documented in the schema. The description reinforces the confirm:false/true workflow and the domain ownership constraint, but adds little parameter-level syntax or format detail beyond what the schema already provides.

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 states a specific verb and resource: it applies AI Visibility fixes to a customer's own hosted WordPress site, and names the concrete changes (structured data, meta description, FAQ page). This is clearly distinguishable from read-only checks and planning tools such as plan_ai_visibility_fixes.

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 two-step usage: call with confirm:false to preview, then call with confirm:true only after the user clearly says yes. It also states the domain must be one of the user's own Squish-hosted WordPress sites, leaving no ambiguity about prerequisites or confirmation.

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

All Squish 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?