Skip to main content
Glama

netcafe-build

by com.ainetcafe

Build and deploy a web app from a description

build_app

Turn one plain-language description into a LIVE single-page web tool: code is generated, deployed to managed hosting with HTTPS, and listed — you get the public URL in ~1-2 minutes. Best for tool-style apps: calculators, converters, checklists, timers, generators, small games. Async — poll with check_job. Example — tools/call build_app {"description":"a tip calculator web app"} → poll check_job

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameNoOptional short app name (defaults to the description).
refineNoSlug of an app you built earlier (e.g. "u-1a23e679") to modify instead of building from scratch — describe only the change in `description`.
visibilityNo"public" (default, listed in the store) or "unlisted" (URL-only, not in the store).
descriptionYesWhat the tool should do, in any language. Be specific about inputs/outputs.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

TDQS

A4.4/5.0
Behavior5/5

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

Annotations are all false/neutral, so the description carries full burden. It discloses key behaviors: code generation, managed hosting, HTTPS, public listing, ~1-2 minute turnaround, and async polling. Also shows how to modify a prior app via 'refine' and gives a runnable example.

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 a compact paragraph with no wasted words. It front-loads the main purpose and then provides usage context, async note, and an example—all valuable. Well-structured despite being multi-sentence.

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?

The tool is moderately complex (async, deployment, multiple params), and the description covers the core flow: input description, deploy, get URL, poll. It does not detail the output schema (which exists) or error cases, but is sufficient for an agent to invoke correctly.

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 parameters are fully documented. The description adds a working example for 'description' and clarifies 'refine' semantics, but does not add much beyond the schema. Baseline 3 is appropriate.

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?

Description uses a specific verb ('Turn ... into a LIVE single-page web tool') and clearly states the resource (web app) and outcome (deployed, HTTPS, listed, public URL). It distinguishes itself from sibling tools like check_job and get_app by focusing on creation and deployment.

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?

Provides explicit best-fit guidance ('Best for tool-style apps') and lists examples. Instructs the async workflow ('Async — poll with check_job') and gives a concrete example call. It doesn't explicitly state when not to use, but the context is clear.

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

All netcafe-build toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.1/5.0
Disambiguation4/5

Most tools target distinct resources: build_app creates new apps, get_app/list_apps retrieve app info, submit_project handles existing repos, project_status tracks submissions, and check_job polls job status. However, check_job's description references tools not present on this server (deep_research, translate_pdf, make_slides), which could cause agents to misuse it for unrelated job types.

Naming Consistency3/5

The majority follow a verb_noun pattern (build_app, check_job, get_app, list_apps, submit_project), but project_status breaks the pattern as a noun phrase, and what_can_you_do is a question-style outlier. The inconsistency, while not chaotic, prevents a perfectly predictable naming scheme.

Tool Count4/5

Seven tools is a reasonable number for a hosting/build platform, covering the main actions without feeling bloated. The presence of two status-checking tools and a meta-tool (what_can_you_do) is slightly redundant but not problematic.

Completeness3/5

The set covers creation (build_app, submit_project) and reading (get_app, list_apps), but lacks update/delete operations for apps, leaving the lifecycle incomplete. Additionally, check_job references job types (deep_research, translate_pdf, make_slides) that do not correspond to any tools in this set, suggesting an incomplete or mismatched surface relative to its documentation.

Resources