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

Annotations already declare idempotentHint=true and destructiveHint=false, but the description adds significant behavioral details: it mentions cost implications ('subject to storage quota and media budgets'), explains the output format ('Returns a signed image URL, not inline image bytes; fetch it without credentials'), and clarifies a limitation ('Does not preview final alpha quality'). These details go beyond what annotations provide and help the agent understand side effects and usage constraints. No contradictions with annotations are present.

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?

The description is concise and well-structured: three sentences that front-load the core purpose, then cover cost/limitations and output format. Each sentence adds essential information without redundancy. It is neither overly verbose nor under-specified, and the most critical detail (what it does) appears first.

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 that an output schema exists (signal: has output schema: true) and the input schema is detailed, the description covers all necessary context for a preview tool: it states the output type (signed URL), cost/budget implications, and the limitation regarding alpha quality. It does not need to explain return values since the output schema presumably does. The description is sufficient for an agent to decide whether to use this tool and what to expect.

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?

The description does not elaborate on the parameters, and schema description coverage is 0% (the tool description itself mentions no parameters). However, the input schema provides thorough descriptions for both parameters (max_frame_size and timestamps_seconds), including constraints and defaults. The description does reinforce the 12-timestamp limit ('at up to 12 timestamps'), but it adds no new semantic value beyond what the schema already explains. Thus, a baseline score of 3 is appropriate.

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: 'Get a labeled contact sheet at up to 12 timestamps, with actual source times.' It specifies the resource (video), the action (preview), and key constraints. It also distinguishes itself from siblings by noting it 'Uses no AI or credits,' setting it apart from generation tools like generate_video. This makes the purpose unambiguous and easily differentiated.

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 description provides useful context for when to use this tool: it emphasizes that it uses no AI or credits and is subject to storage quota and media budgets, implying it's a lightweight preview option. It also warns that it 'Does not preview final alpha quality,' suggesting it's not for final output assessment. However, it does not explicitly name alternatives like generate_video or state conditions for choosing this over them, leaving some inference to the agent.

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