ai_videoGenerate an 8-second AI video clip with native audio (Google Veo 3.1 Fast). ~$0.50. Takes 1-4 minutes.
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | Scene description: subject, action, camera, style | |
| aspect_ratio | No | 16:9 (default) | 9:16 (Shorts/Reels) | Auto |
| Name | Required | Description | Default |
|---|---|---|---|
| result | No |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond annotations (readOnlyHint=false, destructiveHint=false), the description discloses cost (~$0.50), generation time (1-4 minutes), and the specific model/audio feature. This adds useful behavioral context that annotations do not provide.
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, front-loaded sentence followed by two brief fragments. It conveys the essential action and key constraints without unnecessary words, earning every character.
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 an output schema exists, return values are already covered. The description covers the tool's purpose, duration, audio feature, cost, and latency, which is sufficient for a two-parameter generation tool with good schema and annotation coverage.
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 100% coverage, documenting both 'prompt' and 'aspect_ratio' with descriptions. The description itself does not add parameter-level meaning, so the baseline of 3 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 uses a specific verb ('Generate') and clearly identifies the resource ('8-second AI video clip with native audio'). It also distinguishes itself from sibling tools like ai_image and ai_music by specifying the video output and model (Google Veo 3.1 Fast).
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 this tool is for creating AI video clips, but it does not explicitly say when to use it over alternatives or provide exclusions. Context from sibling tool names helps, but the description itself lacks explicit usage guidance.
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.
Four image generation tools, three video tools, and five 'ask' tools create significant overlap. Although descriptions specify the model, an agent must carefully compare prices and capabilities to choose correctly, making misselection likely.
All tool names use snake_case, but patterns are mixed: some start with verbs (remove_bg, scrape_page), some with nouns (crypto_prices, market_snapshot), and many use ai_/ask_ prefixes. Model suffixes like flux, gpt, pro, kling are descriptive but not systematically applied.
24 tools is heavy, inflated by near-duplicate variants for image, video, and LLM queries. While the broad scope justifies a large count, the redundant tools could have been consolidated.
The toolset covers a wide range of media and data tasks: image, video, music, voice, vision, LLM, web, crypto, domain, and endpoint discovery. Notable gaps like speech-to-text or image editing exist, but the surface is fairly complete for a general-purpose media toolkit.