Search apps and games and get short AppAgg summaries with links to full pages.
Scored across 3 tools
Each tool covers a clearly different mode: lookup by ID (get_app_summary), search by name (search_apps), and browse/rank listings (new_and_deals). The descriptions explicitly cross-reference each other, telling the agent when to switch tools (e.g. 'To find a named app, use appagg_search_apps'). No plausible overlap remains.
All three tools use the same appagg_ prefix plus a consistent snake_case verb/resource pattern (get_app_summary, search_apps, new_and_deals). Names are predictable and readable.
Three tools is lean but each covers a distinct retrieval mode (search, browse/rank, detail lookup), so none feels redundant. A slightly larger surface (e.g. developer or category listing) could be justified, but the scope is well matched to a search/lookup server.
The core lifecycle is covered: discover via search, browse curated lists, then fetch full details by ID. Minor gaps exist (no developer-scoped listing, category browse, or platform enumeration), but agents can work around these via search and the linked AppAgg pages.
Get a short app or game summary by AppAgg ID with a link to the full AppAgg page. Take the AppAgg ID from appagg_search_apps or appagg_new_and_deals results, or from the number at the end of an AppAgg page URL.
| Name | Required | Description | Default |
|---|---|---|---|
| appagg_id | Yes | AppAgg ID, a positive integer, for example 39642239. |
| Name | Required | Description |
|---|---|---|
| app | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only, non-destructive, and closed-world behavior, so the description adds rather than duplicates. It contributes meaningful context on what comes back ('a short' summary plus a link to the full page), setting expectations that this is not the full listing. It says nothing about missing/invalid IDs or link accessibility, which keeps it below a 5.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with the action and resource, then the ID provenance. Every clause carries information; nothing is redundant with the name or title.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
A single required parameter with full schema coverage, an output schema for return values, and annotations for safety profile. The description supplies the one thing structured fields can't: where IDs come from and what the payload represents, which is sufficient to invoke correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3. The description goes beyond the schema by documenting acceptable sources of the ID (search results, deals results, trailing number in an AppAgg URL), which tells the agent how to produce a valid value rather than just the type and range.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ('Get a short app or game summary by AppAgg ID') plus the returned artifact ('a link to the full AppAgg page'). Sibling tools are named and are clearly different operations (search and deals listing vs. by-ID summary), so the agent can route without opening schemas.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly tells the agent how to obtain the required ID: 'from appagg_search_apps or appagg_new_and_deals results, or from the number at the end of an AppAgg page URL.' That establishes when this tool is the right follow-up call. No explicit exclusions or failure cases are stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List the best apps and games released in the last 30 days or coming soon as pre-orders (NEW), or currently on sale (DEAL), for a platform, ranked by AppAgg Score, with links to full AppAgg pages. Use it for questions like 'best new Android games' or 'iOS apps on sale today'. To find a named app or game, use appagg_search_apps.
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | Results page, from 1 to 25. | |
| type | Yes | NEW: released in the last 30 days or open for pre-order. DEAL: on sale now. | |
| price | No | free: costs nothing now; paid: costs more than 0 now; any: both. | any |
| platform | No | Store or platform. all: every store; apps or games: every store, only apps or only games; android, ios, macos, and windows also have -apps and -games variants; ps: PlayStation; epic: Epic Games Store; meta: Meta Quest. | all |
| min_discount | No | DEAL only: smallest discount in percent, for example 50. |
| Name | Required | Description |
|---|---|---|
| page | Yes | |
| items | Yes | |
| next_page | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnly, non-destructive, closed-world), so the description's added value is in disclosing result ordering (AppAgg Score) and the 30-day/pre-order content window, which the schema does not state. It leaves pagination behavior and total result counts unmentioned, which keeps it from a 5.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences, zero filler: capability and content scope first, then concrete usage examples, then the disambiguation pointer to the sibling. 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.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 5-parameter filtered list tool with an output schema (so return shape needn't be explained) and annotations covering safety, the description is complete: it covers content scope, ordering, examples, and sibling routing. The only omission, pagination, is already handled by the `page` parameter's own schema documentation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% and the enums for `type`, `price`, and `platform` are already richly documented in the schema, so the description correctly relies on them. It reinforces 'currently on sale (DEAL)' but adds no syntax or constraint detail (e.g. min_discount interaction with type) beyond what structured fields provide. Baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ('List the best apps and games') plus the exact content window (released in last 30 days, pre-orders, or currently on sale) and ranking basis (AppAgg Score). The NEW/DEAL split maps directly to the required `type` parameter, so an agent can tell immediately what this tool returns versus the search sibling.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Gives concrete example questions ('best new Android games', 'iOS apps on sale today') that anchor the intended query shape, and explicitly routes named-entity lookups to appagg_search_apps. That is an explicit when-to-use plus a named alternative with the condition that selects it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search AppAgg by app, game, or developer name across all stores and return short summaries: AppAgg ID, title, developer, platform, price, discount, store rating, AppAgg Score, and a link to the AppAgg page. Use it when the user names an app, game, or developer, or wants to compare one title across stores. For lists of new releases or deals, use appagg_new_and_deals.
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | Results page, from 1 to 25. | |
| query | Yes | App, game, or developer name in plain words, for example 'stardew valley' or 'rockstar games'. Words starting with @ are not allowed. |
| Name | Required | Description |
|---|---|---|
| page | Yes | |
| items | Yes | |
| next_page | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is clear. The description adds that results are short summaries across all stores and lists returned fields, but does not add meaningful behavioral context beyond that, such as pagination behavior or result limits (the schema already constrains page).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two tightly written sentences, front-loaded with the search scope and return summary, followed by the usage guidance and alternative. Every sentence earns its place with no filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With annotations covering safety, 100% schema parameter coverage, and an output schema for return values, the description is nearly complete for an agent to invoke it correctly. The only notable gap is the lack of explicit guidance on when to prefer appagg_get_app_summary over this search tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so both the query and page parameters are already well documented in the input schema. The description repeats the query semantics ('app, game, or developer name') but adds no format or usage detail beyond what the schema provides, making baseline 3 appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb and resource ('Search AppAgg') and specifies the searchable fields (app, game, developer name) plus result scope ('across all stores'). It distinguishes itself from appagg_new_and_deals by noting it returns short summaries for named entities, but it does not explicitly differentiate from appagg_get_app_summary beyond the word 'short summaries'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It gives explicit usage conditions: use when the user names an app, game, or developer, or wants cross-store comparison. It also names an alternative ('For lists of new releases or deals, use appagg_new_and_deals'), though it does not address the other sibling appagg_get_app_summary.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
appagg_get_app_summary1 field changedInput schema / properties / appagg_id / descriptionAdded value: +"AppAgg ID, a positive integer, for example 39642239."appagg_new_and_deals5 fields changedInput schema / properties / min_discount / descriptionAdded value: +"DEAL only: smallest discount in percent, for example 50."Input schema / properties / page / descriptionAdded value: +"Results page, from 1 to 25."Input schema / properties / platform / descriptionAdded value: +"Store or platform. all: every store; apps or games: every store, only apps or only games; android, ios, macos, and windows also have -apps and -games variants; ps: PlayStation; epic: Epic Games Store; meta: Meta Quest."Input schema / properties / price / descriptionAdded value: +"free: costs nothing now; paid: costs more than 0 now; any: both."Input schema / properties / type / descriptionAdded value: +"NEW: released in the last 30 days or open for pre-order. DEAL: on sale now."appagg_search_apps2 fields changedInput schema / properties / page / descriptionAdded value: +"Results page, from 1 to 25."Input schema / properties / query / descriptionAdded value: +"App, game, or developer name in plain words, for example 'stardew valley' or 'rockstar games'. Words starting with @ are not allowed."appagg_new_and_dealsappagg_get_app_summary2 fields changedOutput schema / $defs / PublicAppCard / properties / appagg_scoreAdded value: +{
+ "description": "AppAgg Score: formatted value and tier.",
+ "title": "Appagg Score",
+ "type": "string"
+}Output schema / $defs / PublicAppCard / requiredPrevious value: -[
- "appagg_id",
- "title",
- "developer",
- "platform",
- "public_url"
-]New value: +[
+ "appagg_id",
+ "title",
+ "developer",
+ "platform",
+ "public_url",
+ "appagg_score"
+]appagg_search_apps2 fields changedOutput schema / $defs / PublicAppCard / properties / appagg_scoreAdded value: +{
+ "description": "AppAgg Score: formatted value and tier.",
+ "title": "Appagg Score",
+ "type": "string"
+}Output schema / $defs / PublicAppCard / requiredPrevious value: -[
- "appagg_id",
- "title",
- "developer",
- "platform",
- "public_url"
-]New value: +[
+ "appagg_id",
+ "title",
+ "developer",
+ "platform",
+ "public_url",
+ "appagg_score"
+]appagg_get_app_summaryappagg_search_apps
Add one secure layer between your agents and this server.