categoriesReturn Tenor's GIF browse categories (e.g. trending, featured) with representative GIF previews; filterable by locale, type, and content safety level.
| Name | Required | Description | Default |
|---|---|---|---|
| type | No | ||
| locale | No | ||
| contentfilter | No |
| Name | Required | Description | Default |
|---|---|---|---|
| tags | No | Category list |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds context about filterable parameters and representative previews, but does not disclose rate limits, data freshness, or other behavioral traits beyond the annotations.
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?
Single sentence efficiently conveys the tool's purpose, key features, and filter options. No redundancy or unnecessary detail.
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?
While the output schema exists (reducing need to describe returns), the description lacks details on parameter values and cannot fully guide an agent on correct inputs. The tool is simple but parameter semantics are missing.
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 0%, so description should fully explain parameters. It mentions locale, type, and content safety level as filter options, but does not specify allowed values, formats, or defaults for any parameter.
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?
Description states it returns Tenor's GIF browse categories with representative previews, which is clear. However, it does not explicitly differentiate from sibling tools like search_suggestions or trending_terms, leaving room for ambiguity.
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?
Description provides no guidance on when to use this tool versus alternatives, nor any prerequisites or exclusions. It only implies usage for browsing categories.
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.
Several tools have nearly identical purposes: autocomplete and search_suggestions both return query completions, ask_pipeworx and ask_pipeworx_beta are currently identical, and ai_visibility_check overlaps with scan_competitor_ai_presence. The detailed descriptions help for some, but the overlapping clusters create real confusion for an agent selecting a tool.
Naming is a mix of single-word nouns (search, featured, posts, categories) and snake_case verb phrases (resolve_entity, compare_entities, ask_pipeworx), with modifier suffixes like _beta and _grounded. While the snake_case is consistent where used, the overall pattern is not uniform across the server.
38 tools is far too many for a server named 'Tenor' whose core GIF API needs only a handful. Much of the surface belongs to Pipeworx data, polymarket analytics, memory, and subscriptions—scope that belongs in a different server or a clearly separated package.
The Pipeworx side is remarkably complete: query (ask_pipeworx), grounded answers, deep research, entity profiles, comparisons, validation, discovery, memory, subscriptions, and specialized polymarket tools all cover their domain thoroughly. The Tenor side has search, browse, categories, trending, suggestions, and post retrieval—no critical dead ends.