guichet

submit_pwa

Idempotent

Submit one progressive web app for review. Writes to the moderation queue and emails a receipt to contact_email; a human reviews it before anything is published. Free review takes up to four weeks. Requires idempotency_key: replaying the same key returns the first submission instead of creating a duplicate. Returns submission_id, a handle valid for 30 days, after which get_submission_status and create_pro_launch_checkout reject it. Holding the handle authenticates nobody. Submit apps that exist and that you can name; the queue is read by a person.

Input Schema

TableJSON Schema

Name	Required	Description
`url`	Yes	The app's public URL. A bare domain is accepted and normalised to https://.
`name`	Yes	The app's name, as its makers write it.
`message`	No	Anything else the reviewer should know.
`category`	No	One of the catalog categories. If omitted or unknown, the entry is filed for manual categorisation.
`description`	No	What the app does, in the submitter's words. 25 words or more, and five or more tags, is what a listing needs to be indexable.
`screenshots`	No	URLs of screenshots hosted by the submitter. The directory never re-hosts imagery it does not own.
`contact_email`	Yes	Where the review outcome is sent. Must be an address the submitter can read.
`idempotency_key`	Yes	A caller-chosen key. Replaying this tool with the same key returns the first result instead of creating a second entry. MCP defines no idempotency mechanism, so this is an application argument, not a protocol header.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`url`	Yes
`name`	Yes
`status`	Yes
`session`	No
`category`	Yes
`replayed`	Yes
`next_step`	Yes
`review_time`	Yes
`submission_id`	Yes
`handle_expires_at`	Yes
`category_needs_review`	Yes

TDQS

A4.7/5.0

Behavior5/5

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

Annotations provide readOnlyHint=false, idempotentHint=true, and destructiveHint=false; the description adds valuable specifics: writes to the moderation queue, emails a receipt, human review before publication, 30-day handle expiry, and 'holding the handle authenticates nobody.' No contradiction with annotations.

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?

Every sentence earns its place: primary action and side effects first, then timeline, idempotency, handle lifetime, authentication non-effect, and eligibility. Dense but not bloated, and the most decision-relevant facts are front-loaded.

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?

For an 8-parameter write operation, the description covers process, human-review expectations, idempotency behavior, handle expiry, and authentication semantics. The output schema handles return shape, so nothing critical is missing.

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 100%, so the schema carries most parameter meaning. The description still adds behavioral context beyond the schema by tying contact_email to a receipt email and spelling out the idempotency_key replay semantics as an application-level mechanism rather than a protocol feature.

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 states a specific verb and resource: 'Submit one progressive web app for review.' It distinguishes itself from read/search siblings by describing the moderation queue, receipt email, and human review pipeline, and references related tools only for handle-lifetime behavior.

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?

Gives clear context for use: human-reviewed queue, four-week timeline, and 'Submit apps that exist and that you can name' as an eligibility guideline. It does not explicitly state when not to use the tool or name an alternative like get_submission_requirements, so it stops short of full alternative routing.

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

All guichet tools Inspect

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

A4.7/5.0

Disambiguation5/5

Each tool targets a distinct resource and action: searching the catalog, fetching a single listing, checking submission requirements, submitting an app, checking submission status, and upgrading to Pro. There is no meaningful overlap between any two tools.

Naming Consistency5/5

All tool names follow a consistent lowercase snake_case verb-first pattern: get_*, search_*, submit_*, create_*. Objects are clearly distinguished (pwa vs submission), and the naming makes the tool's purpose predictable.

Tool Count5/5

Six tools is well-scoped for a submission-and-catalog server. Each tool covers a necessary step in the workflow without redundancy or bloat.

Completeness5/5

The server covers the full core lifecycle: requirements lookup, submission creation, status tracking, paid upgrade, catalog search, and catalog detail retrieval. There are no obvious dead ends for the stated purpose, and optional operations like editing or canceling a submission are not clearly required.

Resources

Need Help?