SoraMCP

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

With no annotations provided, the description carries the full burden and successfully discloses key behavioral traits: duration constraints (4/8/12 seconds vs 10-25 for v1), pixel-based resolution control specifics, and return value structure (Task ID, URLs, state). It could clarify whether this is synchronous vs asynchronous given the existence of the _async sibling, but otherwise provides solid behavioral context.

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?

Well-structured with clear information hierarchy: capability summary, specific differentiators, bulleted usage criteria, explicit alternative recommendation, and return value summary. Every sentence serves a purpose; front-loaded with version and channel differentiators. No redundant or wasteful language.

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 the 100% schema coverage, presence of output schema, and 5 parameters with clear enum values, the description provides complete contextual coverage. It addresses the 'partner channel' business logic, contrasts capabilities with v1 siblings, and summarizes return values appropriately without needing to replicate full output schema details.

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?

While the input schema has 100% coverage (baseline 3), the description adds semantic value by contextualizing parameter choices - explaining that specific resolutions like '1280x720' are ideal for 'quick video generation with specific resolution requirements' and linking duration options to the tool's intended use case, adding meaning beyond raw schema specifications.

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 explicitly states 'Generate an AI video using Sora Version 2 (partner channel)' - providing specific verb (Generate), resource (AI video), and distinguishing version/channel context. It clearly differentiates from sibling v1 tools by specifying 'Version 2' and 'partner channel' characteristics.

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?

Includes an explicit 'Use this when:' section with three specific scenarios (precise resolution control, shorter videos, partner channel). Critically, it explicitly names alternatives: 'For longer videos (10-25 seconds) or character-based generation, use the version 1 tools (sora_generate_video, etc.) instead,' providing clear when/when-not guidance.

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