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

Annotations only declare readOnlyHint=false with non-destructive and non-open-world flags; the description adds substantial behavior beyond that. It discloses the returned artifacts (link and QR SVG), the 7-day link expiry, the no-login phone flow, immediate upload, and the onboarding prerequisite. It leaves the failure mode when onboarding is incomplete unstated.

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 core action is front-loaded, but everything is packed into one run-on sentence chained with commas and a colon, mixing purpose, UI behavior, expiry, and prerequisites. Splitting these into two or three short sentences would make it scannable without adding length.

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 correctly carries the return-value burden by naming the link and QR SVG, plus the expiry window and the prerequisite. For a one-parameter creation tool this is generally complete, though the response shape (e.g. whether the shoot sheet text is also returned) remains slightly ambiguous.

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% for the single parameter, so the baseline is 3. The description's 'topic from the brand profile' and 'in the brand language' echo the schema's own wording rather than adding new meaning such as length guidance or how the profile is resolved.

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 states a concrete verb and artifact: write a 4-6 line shoot sheet for a topic from the brand profile and return an openable link plus a QR code SVG. That is clearly distinct from siblings like make_video, make_carousel, or get_shoot, so an agent can route to it without opening the 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?

Usage context is implied rather than stated: the 'phone, no login, 7 days' framing suggests a self-service on-location shoot, and 'needs a finished onboarding' is a real prerequisite. However, no sibling is named as an alternative, and there is no explicit when-not guidance (e.g. versus make_video or get_shoot).

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