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

Annotations only supply readOnlyHint and openWorldHint, so the description carries real weight and does well: it discloses the 60 s clip limit, 20 MB size cap, and payment/cost model (x402, $0.06 USDC per call, $0.012 for typed questions). The pricing is slightly muddled between 'per question' and 'per call' but the operational constraints are clearly surfaced.

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-loaded with purpose and mechanism before modes, limits, and pricing. Every clause carries information, though the cost is stated somewhat redundantly (both per-question and per-call USDC figures) which slightly bloats the tail.

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, and the description compensates by describing the answer form (plain language with timestamps). With zero required params, the agent needs to know a source (url or file_base64) is mandatory, which is implied but not stated; otherwise limits, modes, and cost make it complete enough for a moderate-complexity tool.

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 80%, so the schema already documents url, frames, question, questions, and file_base64. The description adds useful constraints for the file inputs (60 s clips, 20 MB) but doesn't clarify url-vs-file_base64 exclusivity or the frames parameter, so it adds only marginal value over the schema.

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 ("Ask questions about a video") and goes further by describing the mechanism: frame sampling with timestamps, soundtrack transcription, plain-language answers. It's clear what the tool does, though it never explicitly differentiates itself from the nearby vision_ask/transcribe siblings.

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 distinguishes two usage modes (open-ended questions vs typed yes/no/choice/score questions routed to Clef-Omni) and implies the calibrated-answer use case, which is genuinely useful. However it names no alternatives or when-not conditions (e.g., static images should use vision_ask), leaving sibling routing to inference.

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