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

Annotations already cover readOnly and openWorld, so the bar is lower. The description adds genuinely useful context beyond them: the per-call price ($0.006 USDC via x402) and supported output formats, which an agent needs before committing to a paid call. It stops short of describing return payloads or pagination.

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, zero filler, with the core operation front-loaded before constraints and cost. Every sentence carries distinct information.

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 does not explain what comes back (base64 by default vs. share links, though the store param hints at this). Otherwise it covers modes, formats, size limits, and pricing adequately for a 9-parameter read-only 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 100%, so baseline is 3. The description adds real constraints the schema omits, notably the width range 64-1920 px and the format set JPEG/PNG/WebP, plus the count semantics ('up to 10 evenly spaced').

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 ('grab still frames from a video') and defines the two operating modes (single frame at a time, or up to 10 evenly spaced frames for a storyboard). An agent can immediately distinguish this from siblings like media_gif, media_trim, or media_convert.

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 two modes imply when to use 'at' versus 'count', and the storyboard framing gives some intent guidance, but there is no explicit when-not or named alternative (e.g., use media_gif for animation, media_trim for clipping). Usage is implied rather than stated.

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