Skip to main content
Glama
applyra-io

@applyra/mcp-server

by applyra-io
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

simulate_metadata

Score a draft app listing before publishing, compare its ASO health and gain or loss against the app's live listing, or test metadata without an app.

Instructions

Score a listing that does not exist yet, on the same engine that audits the real ones, and see the gain or loss against the app's current score. WITH app_id: every field you leave out is read from that app's live listing AND its real context (rating, screenshots, age, languages), so { app_id, title } is a complete request and the delta is meaningful. This is the mode to use to answer "is my draft better than my listing". WITHOUT app_id: you must pass store, country and lang, and the context defaults to a listing NOBODY HAS PUBLISHED: no rating, no screenshot, one language. That deliberately floors the appeal axis, so the global score is NOT comparable to a real app's score and you must not present it as one. Compare the coverage axis instead, or pass context yourself to describe the app you have in mind. context works in both modes: any key you send overrides, any key you omit keeps the app's value (or the blank default). Returns app (null without app_id), aso_health with the three axes and the tier, delta against the app's stored score (null for a draft from scratch, and each axis is independently null when it was never computed), flags[], the saved run, and notes[] for anything wrong with the request that did not stop it (a kw_field sent for a Google Play listing, which has none, is ignored and reported there). words_probed is how many words the run weighed; words_fetched is how many of those had to be read from the store for the first time. words_fetched: 0 means everything was already known and the call was fast; a high one is why a call took several seconds, and it warms the cache for everyone afterwards. Expect a few seconds per call. Check the draft with check_metadata first, and change something meaningful between two calls rather than polling it. Re-read a past run in full with get_metadata_simulation, or list them with list_metadata_simulations.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
langNoBCP-47 language code. Required only without app_id.
storeNoApp store. Required only without app_id: with one, the market comes from the app.
titleNoApp name
app_idNoThe application internal ID (numeric, from list_applications). Its live listing fills every field you omit, and its score is what the delta is measured against.
contextNoWhat the listing has going for it beyond its text, merged over the app's real values. Send one key alone to ask a what-if, e.g. { days_since_update: 0 } for "what if I shipped today".
countryNoISO country code. Required only without app_id.
kw_fieldNoiOS keywords field, comma separated. Google Play has no such field.
subtitleNoThe subtitle on iOS, the short description on Google Play
descriptionNoThe full/long description

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.5.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations declare openWorldHint=true and readOnlyHint=false, and the description adds real behavioral context the annotations cannot: expected latency ('a few seconds per call'), cache-warming via words_fetched, the deliberate blank-default context that floors the appeal axis, and the warning not to present a draft's global score as comparable. It flags partial-failure reporting through notes[].

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 the core purpose and the two modes, and every sentence carries information (return shape, caveats, latency, alternatives). It is dense and somewhat long for a single description, but not padded with filler.

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?

There is no output schema, yet the description enumerates the return payload in detail (app, aso_health axes and tier, delta with per-axis nulls, flags, saved run, notes, words_probed/words_fetched). Combined with the mode and caveat coverage, an agent has everything needed to call and interpret it.

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 the schema already documents every parameter, including the app_id/required-only-without-app_id rules and the context sub-fields. The description reinforces the override/merge semantics of context but adds little that isn't already in the schema's own descriptions, so the baseline 3 applies.

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?

States a specific verb and resource ('score a listing that does not exist yet') and immediately anchors it to a concrete outcome (gain/loss vs the app's current score). It also distinguishes itself from siblings by positioning the engine as the same one that 'audits the real ones'.

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?

Explicitly branches on whether app_id is present, telling the agent exactly what each mode means and which question it answers ('is my draft better than my listing'). It names alternatives with conditions: check_metadata first, get_metadata_simulation to re-read, list_metadata_simulations to list.

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