Skip to main content
Glama
carlosphyll

phyll

by carlosphyll
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

start_review

Start a UX review of a running app by scanning its source code, creating a report folder, and providing step-by-step instructions to find and fix usability issues.

Instructions

Start a Phyll review of an app that is already running. Call it first, once, when the person asks to review, audit or improve the UX of an app. It scans the project's source, creates the report folder and returns the method to follow step by step. It needs a Phyll account on this computer (npx phyll login or npx phyll signup) and uses one of the account's reviews.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesAddress where the app runs and answers, such as http://localhost:3000. Start the app first if it is not running.
jobsNoThe two or three things the end user comes to do, as the person named them, such as Book a haircut. Leave it out when the person did not say.
nameNoName of the product, for the report's project on agentphyll.com. When left out, it comes from .phyll/config.json, then from the folder's name.
userNoWho uses the app, in the person's words, such as barbershop customers booking on a phone. Leave it out when the person did not say.
languageNoLanguage of the report as a code, such as en or pt-BR. Use the language the person writes in. When left out, it comes from the project's .phyll/config.json, then from this computer's language.
project_dirNoPath to the project folder, when it is not the folder the agent runs in. A relative path starts from that folder.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv0.4.6
    • changedInput schema / properties / jobs / description
      Previous value: -"The core jobs of the app, when the person named them"New value: +"The two or three things the end user comes to do, as the person named them, such as Book a haircut. Leave it out when the person did not say."
    • changedInput schema / properties / language / description
      Previous value: -"Language of the report, such as en or pt-BR. Use the language the person writes in."New value: +"Language of the report as a code, such as en or pt-BR. Use the language the person writes in. When left out, it comes from the project's .phyll/config.json, then from this computer's language."
    • changedInput schema / properties / name / description
      Previous value: -"Name of the product, for the report's project"New value: +"Name of the product, for the report's project on agentphyll.com. When left out, it comes from .phyll/config.json, then from the folder's name."
    • changedInput schema / properties / project_dir / description
      Previous value: -"The project folder, when it is not the folder the agent runs in"New value: +"Path to the project folder, when it is not the folder the agent runs in. A relative path starts from that folder."
    • changedInput schema / properties / url / description
      Previous value: -"Where the app runs, such as http://localhost:3000"New value: +"Address where the app runs and answers, such as http://localhost:3000. Start the app first if it is not running."
    • changedInput schema / properties / user / description
      Previous value: -"Who uses the app, when the person said it"New value: +"Who uses the app, in the person's words, such as barbershop customers booking on a phone. Leave it out when the person did not say."
  2. First observedv0.4.5

TDQS

A4.5/5.0
Behavior5/5

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

With no annotations provided, the description carries the full responsibility for behavioral disclosure. It reveals side effects (creates the report folder), prerequisites (app running, account login), resource consumption (uses one account review), and what it returns (step-by-step method). This is transparent for a review-starting operation.

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 three sentences with no filler: it states the action, when to invoke it, what it does, the prerequisite, and the account requirement. The most important information is front-loaded in the first sentence.

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?

Despite no output schema and no annotations, the description makes the tool safe to invoke: an agent knows when to call it, what inputs are expected through the schema, what side effects occur, what is returned, and what external requirements must be met. Nothing essential is missing for a correct first call.

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 description coverage is 100%, so the schema already documents all six parameters well. The description adds no parameter-specific meaning beyond the schema, which matches the baseline expectation of 3.

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 opens with a specific verb-plus-resource phrase, 'Start a Phyll review of an app that is already running,' and explains what happens: scans source, creates report folder, and returns the step-by-step method. It is easily distinguishable from siblings like finish_review and guide because it is explicitly framed as the first call in the flow.

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 direct usage guidance: call it first, once, when the person asks to review, audit, or improve UX. It also states prerequisites (app running, Phyll account logged in). It does not explicitly contrast this with siblings such as guide or scan, but the trigger conditions and sequencing are clear enough.

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

Deploy Server

Other Tools