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

Annotations cover the safety profile (openWorldHint, destructiveHint, non-idempotent), and the description adds that the call is asynchronous, returning a tracked task with a playable result. It says nothing about charges for a paid generation beyond what the schema's maxCostUsd and idempotencyKey fields already imply. No contradiction with annotations.

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?

Three short sentences, front-loaded with the action and then the prerequisite and the return shape. No filler or 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?

With 21 parameters, nested objects, and an output schema present, the description adequately covers the operation, the required catalog lookup, and the async return. It does not disambiguate the many overlapping source inputs (sourceMediaId vs sourceVideoMediaId vs sourceVideoUrl), though the schema handles that.

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 81%, above the high-coverage threshold, so the schema already documents model, prompt, cost, scaleFactor, media slots, and idempotency. The description adds only the model-catalog pointer, which the schema's 'model' description already repeats.

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 and resource ('Upscale an existing video') and scopes it to catalog models that support the operation. It does not, however, distinguish itself from near-siblings like upscale_image, enhance_video_media, expand_video, or convert_video_to_hdr, so an agent must infer the boundary.

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?

It gives one concrete prerequisite: consult get_model_catalog to pick a supported model and its settings. That is useful routing, but there is no when-to-use-this-vs-alternatives guidance, no statement of when upscaling is inappropriate, and no mention of cost/preconditions.

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