Turn movie/TV recommendations into playable trailer pages: permanent, free, every title plays.
Scored across 2 tools
The two tools have clearly distinct purposes: one creates a new list and the other checks an existing list's status. No overlap or ambiguity between them.
Both tools follow a consistent verb_noun pattern (create_list, get_list), making their purposes immediately clear and predictable.
With only two tools, the server feels minimal but usable for its narrow purpose. However, it falls short of the typical well-scoped range of 3-15 tools.
The server covers creation and status checking but lacks update or delete operations, which are notable gaps for managing lists over time.
Turn your movie/TV recommendations into a playable trailer page on zinema.tv and share the link with the user. Each title plays as a full trailer the user can scroll, like a personal cinema session. Links are permanent and free. Returns per-title resolution (echo of what matched, so you can catch mix-ups) and playability. Use it whenever you recommend movies or shows: a page that PLAYS beats a text list.
| Name | Required | Description | Default |
|---|---|---|---|
| items | Yes | Your recommended titles, in the order you want them to play. | |
| title | No | Optional page title, e.g. 'Slow-burn thrillers for tonight'. Plain text, no URLs. | |
| language | Yes | Language of your conversation with the user. Drives trailer language (original-with-subtitles when no dub exists), page wording and localized titles. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond annotations (readOnly=false, idempotent=true, etc.), the description adds valuable behavioral details: links are permanent and free, each title plays as a full trailer, and it returns per-title resolution with an echo to catch mix-ups. This discloses expected side effects and output behavior, significantly aiding an agent's understanding.
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 four sentences, each with a distinct purpose: action/output, user experience, key properties (permanent/free), and usage guidance. There is no filler or redundancy, making it compact and easily skimmable.
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?
With no output schema, the description compensates by clearly stating what the tool returns (per-title resolution and playability). It also covers the main workflow (create, share) and appropriate use cases, making it complete for a tool with simple parameters and a single sibling.
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% with detailed descriptions for all parameters (items, title, language), so the baseline is 3. The description does not introduce new parameter-specific syntax but does hint at the 'items' parameter's role by discussing per-title resolution and playability, which indirectly supports understanding.
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 converts movie/TV recommendations into a playable trailer page on zinema.tv and shares the link. It uses a specific verb ('Turn... into') and identifies the resource and output, distinguishing it from the sibling get_list which retrieves existing lists.
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 explicitly says to use it 'whenever you recommend movies or shows' and explains the benefit over a text list ('a page that PLAYS beats a text list'). It does not explicitly name get_list as an alternative, but the context implies creation versus retrieval, providing clear functional guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Check a zinema list you created earlier: which titles play now. A title that was 'pending' may have become 'playable' (its trailer gets acquired automatically) or 'no_trailer' (none exists anywhere).
| Name | Required | Description | Default |
|---|---|---|---|
| code | Yes | The list code returned by create_list. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds meaningful context beyond the readOnlyHint and openWorldHint annotations by explaining dynamic state transitions from 'pending' to 'playable' or 'no_trailer'. It confirms a read-only operation that reflects changing conditions without contradicting 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?
The description is two well-structured sentences: the first states the tool's purpose, the second explains the possible status transitions. It is front-loaded and contains no redundant or unnecessary words.
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 tool with one parameter and no output schema, the description provides sufficient context about what the tool does and the significance of the statuses. It could be more explicit about the exact return format, but the phrase 'which titles play now' and the status explanations give an agent enough understanding to invoke it 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?
The schema already fully documents the single parameter 'code' as the list code returned by create_list. The description does not add extra parameter details beyond a slight contextual reminder that the list was created earlier, so the baseline for high schema coverage is appropriate.
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 checks a previously created list and reports which titles currently play. It uses a specific verb ('check') and resource ('zinema list'), and it distinguishes itself from the sibling create_list by focusing on inspection rather than creation.
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 implies the tool should be used after create_list by referencing 'a list you created earlier'. It does not explicitly mention when not to use it or name alternatives, but the sibling relationship and wording make the intended usage clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
create_listget_listThe media memory layer for AI agents and their humans. Your AI client gets 29 tools to search your collection, add items, update ratings, preview music, and find patterns across everything you've read, watched, and listened to.
Media memory for AI agents and their humans: books, movies, music, shows, anime, podcasts, games.
TMDB v3: movies, TV, people, trending, discover, genres, credits. Free key.
Personalised book recommendations, filtered to what's on your public library's shelf right now.
Add one secure layer between your agents and this server.