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

Adds substantive traits beyond the annotations: 'SYNC' discloses blocking behavior, 'Costs 10 credits' quantifies the cost, and '0 credits if already upscaled' operationalizes the idempotentHint. It also states the return value (upscaled URL), none of which appears in the structured fields.

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?

Front-loads the purpose and is dense with useful information; every sentence earns its place. The telegraphic fragments ('SYNC. Costs 10 credits.') and uppercase emphasis are slightly cramped but still readable and efficient.

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?

No output schema exists, but the description states the return value, the cost model, both input modes with their prerequisites and provenance, and the sync nature. Nothing needed to invoke it correctly is missing.

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 coverage is 100% and both params are documented, so baseline is 3, but the description adds real meaning: projectId must be a COMPLETED project sourced from list_videos, and r2Key refers to a raw clip with no project whose key comes from create_upload/import_asset_from_url. This goes beyond the schema's terse field docs.

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?

States a specific verb (upscale), resource (video), and outcome (1080p, Topaz) in the first sentence. An agent can immediately distinguish this from sibling video tools like dub_video, create_video, or voice_enhance.

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?

Explicitly enumerates the two source modes, the condition selecting each (COMPLETED project via projectId vs raw clip via r2Key), and where to obtain each input (list_videos, create_upload + PUT, import_asset_from_url). This is exactly the routing guidance an agent needs.

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