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

Annotations are none, so description carries full burden. It discloses async behavior (returns {id, status}), polling via getApiJob, credit billing per second, refund on failure/cancellation, and the result format (new URL and duration). It mentions credit hold and refund policy. It doesn't detail error handling or retry behavior, but covers main behaviors. No contradictions with annotations (none provided).

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?

Description is thorough and well-organized, but somewhat dense and lengthy. It front-loads key info (upscale to 2x, use generated videos) but includes multiple clauses and parentheticals (e.g., 'landscape or portrait (only a square 720x720 would)') that could be simplified. Still, every sentence adds value, and it's not bloated with fluff. A 4 for efficient but slightly overloaded structure.

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 no annotations or output schema, description provides comprehensive context: input constraints, billing, async nature, polling method, result format, and relationship to siblings. It even includes credit cost (0.2 credits/sec). An agent has everything needed to call and interpret the tool correctly, including failure/refund behavior. Very complete.

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 baseline is 3. Description adds value by explaining the video parameter's constraints (7-day, model-specific) and the request_id semantics (idempotency, listGenerations filter). This goes beyond schema, but since schema already covers these, the addition is moderate, not exceptional.

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?

Description clearly states action ('upscale a previously generated video'), resource (video url), and specific effect (2x resolution). It explicitly differentiates from siblings by mentioning createVideo, editVideo, and related tools, and is specific about input constraints (7-day old, 480p vs 720p). No ambiguity about what the tool does.

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?

Provides explicit when-to-use guidance: pass a URL from specific generation tools, ensure source is under 960 pixels, use griffin for generation if upscaling is intended. Clearly states what is NOT accepted (external videos, griffin-hd outputs except square). It doesn't explicitly list alternatives for when not to use, but it thoroughly covers conditions and prerequisites, making it easy for an agent to decide correctly.

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