Adds keywords to an app's tracked set in one storefront. Takes a list or a comma-separated paste. They arrive unscored - scoring costs requests to Apple and happens on the collector's schedule - so do not read a null popularity here as a zero.
| Name | Required | Description | Default |
|---|---|---|---|
| appId | Yes | App Store app id | |
| country | Yes | Storefront code, e.g. us, tr, de | |
| keywords | Yes | The phrases to track. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the annotations, the description reveals that keywords arrive unscored, that scoring is a separate Apple-costing operation on the collector's schedule, and that a null popularity must not be interpreted as zero. This is valuable behavioral context that prevents a likely misinterpretation.
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?
The description is three sentences with no filler. The action is front-loaded, and the scoring warning earns its length by explaining an important non-obvious behavior.
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 simple 3-param mutation with complete schema and useful annotations, the description covers the operation, input format, and post-add behavior. It does not describe return values, and the comma-separated paste ambiguity is a minor gap, so it stops short of a 5.
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?
The schema already documents all three required parameters clearly, so the baseline is 3. The description adds the 'list or comma-separated paste' input nuance, though the comma-separated paste phrasing is slightly inconsistent with the array type, which prevents a higher score.
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 first sentence names the action ('Adds'), the object ('keywords'), the scope ('app's tracked set'), and the storefront constraint ('one storefront'). This clearly separates it from read/list siblings like get_keyword and list_keywords.
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?
The description gives clear context: use this when you want to add keywords to a specific app and storefront. It does not explicitly name an alternative or give a when-not-to-use, but the mutation role is obvious enough from the first sentence.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct resource or analytical view: tracked keywords, single-keyword details, cusp-band work lists, competitor rankings, storefront priorities, and metadata auditing. The descriptions clarify the boundaries between overlapping-sounding tools like list_keywords, cusp_actions, and ranking_keywords.
Several tools follow a clean verb_noun pattern (add_keywords, get_keyword, list_keywords, list_apps, audit_metadata), but others are noun phrases or gerunds (country_priorities, cusp_actions, keyword_competitors, ranking_keywords). Names are readable and meaningful, but the pattern is not consistent across the set.
Nine tools is a well-scoped size for an App Store keyword and ASO research server. Each tool covers a distinct capability without feeling redundant or padded.
The read-side surface is strong: listing apps, keywords, rankings, competitors, and storefront priorities are well covered. However, the tracked-keyword lifecycle is one-directional: add_keywords exists but there is no remove_keywords or update_keywords, leaving agents unable to prune or correct a tracked set.
