Given a filmmaking brief, return the closest intent-routed MCP recommendations and the first servers to connect. Use hosted_only=true when the agent cannot spawn local tools.
| Name | Required | Description | Default |
|---|---|---|---|
| brief | Yes | What you're trying to make, e.g. 'avatar UGC ad with voiceover' or 'search dailies and cut a trailer' | |
| hosted_only | No | Only return hosted remote primary/fallback servers where possible. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of disclosing behavioral traits. It mentions 'intent-routed' and 'first servers to connect,' but does not state whether the operation is read-only, how recommendations are ranked, what happens on no matches, or any potential side effects. This is a minimal disclosure for a recommendation tool.
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 exactly two sentences, with the first sentence stating purpose and the second providing focused parameter guidance. Every word earns its place; there is no redundancy or fluff.
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?
The tool has no output schema, so the description must clarify what is returned. It states 'closest intent-routed MCP recommendations and the first servers to connect,' giving a basic idea of output. However, it lacks details about result structure, ordering, fallback logic, or error handling. Given the simplicity of the tool and sibling context, this is adequate but incomplete.
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% for both parameters, so the schema already documents them. The description adds a usage condition for hosted_only=true, but this largely echoes the schema's description ('Only return hosted remote primary/fallback servers where possible'). No additional meaning is added for the 'brief' 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?
The description clearly states the tool's action ('return') and resource ('closest intent-routed MCP recommendations and the first servers to connect'), providing a specific verb and target. It distinguishes itself from siblings like search_film_mcps by emphasizing intent-routing and server connection, though it does not explicitly name alternatives.
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 gives one parameter-specific usage condition ('Use hosted_only=true when the agent cannot spawn local tools') but offers no guidance on when to choose this tool over sibling tools such as get_film_recommendation or plan_film_stack. The 'Given a filmmaking brief' phrase implies a use case but provides no exclusions or alternative comparisons.
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 target distinct entities (capabilities, playbooks, recommendations, servers, install configs). The only potential confusion is between plan_film_stack and recommend_film_mcps, but their descriptions clarify different scopes: full pipeline vs intent-routed brief.
All tools follow a consistent verb-first snake_case pattern: get_ for singular resources, list_ for plural, plus search_, plan_, recommend_, and submit_. No mixed conventions or vague verbs.
15 tools is at the upper end of the ideal range but each earns its place: search, retrieval, listing, planning, recommendation, install config, and submission. No redundant tools.
Covers the full directory lifecycle: discovery, retrieval, contextual listings, planning, recommendations, install config generation, and submission. Minor gap: there's no explicit list-all-servers endpoint, but search_film_mcps can fulfill that role.
