Tavus MCP Server

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden but reveals little behavioral context. 'Generate' implies a creation/mutation operation, but it doesn't disclose whether this is synchronous/asynchronous (callback_url hints at async), what permissions are needed, rate limits, or what happens to existing videos. It mentions 'fast rendering (limited features)' in the schema but not in the description itself.

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, efficient sentence that front-loads the core action ('generate a video') and key inputs ('using a replica and script or audio'). There is zero wasted text, and it immediately communicates the essential purpose without redundancy.

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 complex mutation tool with 11 parameters, nested objects, no annotations, and no output schema, the description is inadequate. It doesn't explain the video generation process, output format, error handling, or how parameters like background_url and properties interact. The lack of behavioral context and output details leaves significant gaps for an AI agent.

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%, so parameters are well-documented in the schema. The description adds minimal value beyond the schema by mentioning 'replica and script or audio', which aligns with replica_id and the script/audio_url alternatives. However, it doesn't explain parameter interactions (e.g., script vs audio_url exclusivity) or provide additional context beyond what's in schema descriptions.

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 verb 'generate' and resource 'video', specifying it uses a 'replica and script or audio'. It distinguishes from siblings like generate_speech (audio only) and create_lipsync (different process). However, it doesn't explicitly contrast with get_video or list_videos, which are retrieval operations.

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 provides no guidance on when to use this tool versus alternatives like generate_speech (for audio only) or create_lipsync (for syncing existing audio). It doesn't mention prerequisites (e.g., needing an existing replica) or exclusions (e.g., not for editing existing videos). The only implied usage is generating new videos from replicas.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.