discover_tvDiscover TMDB TV shows using advanced filters passed as query params (genre, first_air_date, vote average, network, sort order, etc.). Use genres_tv to get valid genre IDs first.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | Current page number | |
| results | No | Discovered TV shows | |
| total_pages | No | Total pages | |
| total_results | No | Total results |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / additionalPropertiesRemoved value: -trueInput schema / examplesAdded value: +[
+ {
+ "sort_by": "popularity.desc"
+ },
+ {
+ "first_air_date_year": 2022
+ }
+]Output schema / (root)Previous value: -nullNew value: +{
+ "properties": {
+ "page": {
+ "description": "Current page number",
+ "type": "number"
+ },
+ "results": {
+ "description": "Discovered TV shows",
+ "items": {
+ "properties": {
+ "id": {
+ "type": "number"
+ },
+ "name": {
+ "type": "string"
+ }
+ },
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "total_pages": {
+ "description": "Total pages",
+ "type": "number"
+ },
+ "total_results": {
+ "description": "Total results",
+ "type": "number"
+ }
+ },
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnly, idempotent, and openWorld hints. The description adds that it uses query params and lists filter types, which is additional behavioral context. It does not disclose pagination, rate limits, or response structure, but annotations cover safety.
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 a single sentence with a list of filters. It is concise but could be better structured with parameter details or formatting. Every word adds value, but the list is somewhat vague.
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?
Given no documented parameters and only examples, the description should explain how to construct query params and what output to expect. It fails to mention response structure or pagination. An output schema exists but is not described. The tool's complexity warrants more complete guidance.
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 input-schema has no defined properties, only examples. The description lists filter categories (genre, first_air_date, etc.) but lacks exact parameter names, formats, and constraints. With 0 parameters in schema, the description should provide more precise semantics; it does not fully compensate.
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 clearly states the tool discovers TV shows using advanced filters, listing examples like genre, air date, etc. It mentions 'genres_tv' for genre IDs, but doesn't explicitly distinguish from 'discover_movie' or 'search_tv'. However, the verb 'discover' and filter context differentiate it sufficiently.
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 advises using 'genres_tv' first for genre IDs, which is a helpful prerequisite. However, it does not specify when to use this tool over alternatives like 'search_tv' (text search) or 'discover_movie'. Usage context is implied but not explicit.
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.
The tool set blends two unrelated domains (TMDB and Pipeworx). Among Pipeworx tools, several overlap heavily (ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research, suggest_questions) with vague boundaries, making it hard for an agent to pick the right one. TMDB tools are distinct but the overall mixture creates confusion about which domain a request belongs to.
All tools use snake_case, which is consistent. However, naming styles vary widely: TMDB tools use simple noun or verb-first names (movie, search_movie, discover_tv), while Pipeworx tools use longer descriptive phrases with prefixes (ask_pipeworx, polymarket_arbitrage, entity_profile). The pattern is not predictable across the set.
50 tools is excessive for a server named 'Tmdb'. Only about 18 tools are actually TMDB-related; the remaining 32 belong to the Pipeworx ecosystem. This inflates the count and makes the server feel bloated and unfocused, far beyond a well-scoped TMDB server.
The TMDB portion is quite complete (search, discover, details, credits, recommendations, trending, genres, configuration). However, the server's overall scope is muddled—it tries to cover two disjoint domains, so no single domain feels fully fleshed out. There are also some missing TMDB features (e.g., upcoming/now playing) that would require extra discovery. The Pipeworx tools cover data broadly but overlap in coverage.