delete_keywordPermanently delete a tracked Appskyline keyword by id. Idempotent — deleting an already-deleted keyword is a no-op. This stops collecting new ranking snapshots; historical search rows in the *-searches collections are not affected.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Keyword id to delete |
| Name | Required | Description | Default |
|---|---|---|---|
| status | Yes | ||
| keywordId | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds substantial behavioral detail beyond the annotations: idempotence on already-deleted keywords, that only future snapshot collection stops, and that historical rows are unaffected. This is exactly the side-effect information an agent needs for a destructive call.
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, no wasted words, and the primary action and scope are front-loaded. Idempotence and boundary-of-effect details follow naturally without bloating the description.
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 low-complexity tool with one required parameter and an output schema, the description covers what is deleted, key side effects, idempotence, and what is not affected. An agent has everything it needs to call this tool 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 description coverage is 100%, and the single id parameter is already described as 'Keyword id to delete.' The description adds little beyond saying 'by id,' so the schema carries the semantic weight.
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 states a specific verb and resource: 'Permanently delete a tracked Appskyline keyword by id.' It clearly separates this destructive action from read-only and creation siblings like add_keyword, list_keywords, and get_keyword_history.
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 clarifies that the tool stops collecting new ranking snapshots and leaves historical search rows untouched, giving useful context for when it is appropriate. No explicit sibling alternative is named, but the delete-and-stop-tracking purpose is clear.
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.
Most tools cleanly split by entity: apps, keyords, store listing, reviews, search. Potential confusion exists between get_store_isting and get_store_metadata, and show_app_overview vs list_keywords, but the descriptions are sufficiently specific to guide selection.
The set uses lowercase snake_case verb_noun patterns, with get_X for single resources, list_X for collections, add_keyword, search_store_results, and show_app_overview. The mixture of show/get is minor inconsistency, and list_google_play_reviews is a nice exception, but overall it's cohesive.
The domain is built around app tracking, keyword research, store data, and engagement, and 13-14 tools is well within the sweet spot. Few tools feel obviously redundant, and each covers a distinct part of the ASO workflow.
The core read/query workflows are covered: list apps, list keywords, get rankings/history/volume, fetch store listing/metadata, and search. However, add_keyword is the only keyword mutator — there is no delete_keyword or update_keyword — creating a real dead-end for tracked-keyword management. Also review coverage is limited to Google Play alone.