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

Goes well beyond the annotations by disclosing auth requirements (no API key), cost (no credits), rate limiting ('Limited per IP'), input limits (public video, max 15 minutes), output shape (6 JPGs, max 640px), and a privacy quirk (source URL is not returned). The idempotentHint is not echoed, but the added operational context is substantial.

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 compact sentences, each carrying a distinct fact (cost/auth, output specs and limits, follow-up call). The most decision-relevant information — free, no key — is front-loaded.

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 no output schema, the description carries the return-value burden and does so: it says an id is returned and how to use it, and warns the source URL is not returned. It omits expected timing or how long the demo result persists, which would fully close the loop for an async flow.

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 the 'url' parameter is already documented, but the description adds a real constraint on its valid domain — the video must be public and no longer than 15 minutes. That is meaningful input guidance beyond the schema's 'Public video URL'.

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 ('Extracts 6 evenly spaced JPG frames ... from a public video') plus the demo scope, which cleanly separates it from getvideoframes_create_job. An agent can tell this is the no-credential sandbox path without opening either schema.

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?

Gives clear selection context: free/public preview, no API key, no credits, IP-limited, 15-minute cap, and names the follow-up call (getvideoframes_get_demo with the returned id). It stops short of explicitly saying when to switch to create_job (e.g., long videos, production use), leaving that to inference.

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