media_assets_previewReturn one bounded JPEG as MCP image content for visual inspection. Images use the stored visual; videos use the existing thumbnail.
| Name | Required | Description | Default |
|---|---|---|---|
| assetId | Yes | Media asset UUID. UUID string. | |
| maxDimension | No | Maximum preview width or height in pixels (256-1536). |
| Name | Required | Description | Default |
|---|---|---|---|
| asset | Yes | ||
| preview | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint and idempotentHint, so the safety profile is known. The description adds valuable context beyond annotations by specifying the output as a bounded JPEG and the conditional behavior for images vs videos (stored visual vs thumbnail). This clarifies what the agent can expect from the 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?
Two concise sentences, each adding value. The first sentence states the action and result; the second clarifies behavior for different asset types. No wasted words, and the most important information is front-loaded.
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 is simple, has full schema coverage, an output schema, and safety annotations. The description covers the key behavioral distinction (image vs video) and clearly communicates the return format. Nothing critical is missing for the agent to select and invoke this tool 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?
Schema description coverage is 100%, so parameters are well-documented in the schema. The description mentions 'bounded' which relates to maxDimension, but doesn't add new parameter-specific meaning beyond what the schema already provides. Baseline 3 applies.
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 function: 'Return one bounded JPEG as MCP image content for visual inspection.' It specifies the verb (return), the resource (media asset), the output format (JPEG), and the purpose (visual inspection). It also distinguishes itself from siblings by noting the difference between image and video behavior.
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 usage is implied by the phrase 'for visual inspection' and the tool name, but there is no explicit comparison to alternatives or guidance on when not to use it. No exclusions or alternative tool references are provided, so it falls short of a clear contextual distinction.
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 use clear domain prefixes, but several boundaries are fuzzy: clips_get and clips_manage both expose clip/export status, and update_timeline_clip overlaps with timeline_edit_apply for trim/duration changes. Detailed descriptions mitigate this, but an agent could still select the wrong tool for clip inspection or timeline edits.
All names are snake_case and mostly readable, but the server mixes verb-first names (add_text_overlay, delete_timeline_items, update_timeline_clip) with noun-first domain-action names (clips_create, generation_*_create, media_import_*). The domain-prefix pattern dominates, yet the inconsistent verb placement makes the convention only partially predictable.
58 tools is far beyond the 25+ threshold and matches the rubric's 50+ extreme-mismatch example. Even though the domain is broad, this surface would be easier for an agent to navigate if split into focused servers for media, generation, timeline editing, clips, and workflows.
Core video-editing flows are well represented: project creation/inspection, timeline item editing/deletion, media import/upload, AI generation, exports, and clips. However, lifecycle gaps remain—no project update/delete, no media asset deletion, no delete for characters or story kits, and no export cancellation—so some user requests will dead-end.