Delete a category. The accounts, posts and assets that used it are kept and simply lose their category. Owner or admin only.
| Name | Required | Description | Default |
|---|---|---|---|
| category | Yes | Category to delete (id or name) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Goes well beyond the annotations by disclosing the non-cascading behavior — dependent entities survive and merely lose the category reference — and the authorization requirement. destructiveHint already signals destruction, so the description's added value is precisely what gets destroyed and what does not, plus who is allowed to call it.
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 short sentences, each earning its place: the action, the behavioral consequence, and the access restriction. Front-loaded verb+resource with zero filler or repetition of schema content.
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?
Complete for the common case: purpose, effects on dependent entities, and permissions are all covered for a one-parameter mutation. Minor gaps remain — behavior when the category does not exist, resolution of duplicate names, and the response shape, especially given there is no output schema — so it is not a full 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?
Schema coverage is 100% ('Category to delete (id or name)'), so the schema fully documents the parameter. The description adds no additional parameter detail, such as how name collisions are resolved or how id versus name lookup behaves, landing it at the baseline 3.
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 ('Delete a category'), which cleanly distinguishes it from siblings like create_category, update_category, and list_categories. It also differs from other delete tools (delete_tag, delete_assignment, delete_folder) by naming the exact resource.
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 conveys when the tool is appropriate by explaining the postconditions (referencing accounts, posts, and assets are preserved) and the permission constraint (owner or admin only). However, it never names alternatives or states when-not-to-use, leaving the agent to infer the choice versus update_category or other category-scoped tools.
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 has a distinct target resource/action, and the descriptions are unusually explicit about differences (e.g., 'Distinct from the watchlist', 'Separate list from list_tags'). A few pairs are still easy to confuse without careful reading: delete_folder vs delete_folders differ only by singular/plural, and the three download-URL tools (get_post_download_url, get_asset_download_url, get_my_account_post_download_url) plus the category/tag families require attention to pick correctly.
The snake_case verb_noun pattern is followed consistently throughout (list_*, get_*, create_*, update_*, delete_*, set_*, tag_*). Minor deviations: archive_folder and archive_my_accounts also perform restore despite their names, delete_folder/delete_folders split one operation by cardinality, and tag_posts/tag_my_account use a different verb style than the set_* family for metadata mutations.
At 56 tools, this far exceeds the 25+ threshold for 'too many,' even though the server spans multiple subdomains (watchlist, analysis, assignments, folders, my accounts, assets, Drive, categories/tags). Obvious consolidation candidates exist — delete_folder/delete_folders, the three download-URL getters, and the parallel list_my_account_* listers — and the sheer surface is heavy for an agent to navigate.
Core workflows are thoroughly covered with no dead ends: watchlist → analyze → assign → folder → track → approve has full lifecycle support, including reversible archive vs permanent delete choices. Minor gaps exist but are work-aroundable: no create/update for my accounts or models (app-side OAuth/admin only), no way to delete a viral post or a post note, and asset upload only happens in the app.
