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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds genuinely new behavior beyond that: it long-polls for unfinished work, bounded by waitSeconds, and returns a picture plus full-page link per design. It stops short of noting timeout/partial-result behavior when the wait expires.

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?

Two sentences, zero filler, with the state enumeration front-loaded and the waiting behavior second. The nested parenthetical about pictures and links is slightly dense but still readable.

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 at a summary level: statuses, a picture, and a full-page link, plus the stopping reason. What 'picture' is and whether long-poll expiry changes the shape remain unclear, keeping it out of the top band.

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 50%: waitSeconds is documented in the schema, while projectId is only typed as a UUID with no description. The description adds real meaning for waitSeconds by explaining that it waits for unfinished work before answering; it adds nothing for projectId beyond its name. Partial compensation justifies a 3.

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 names a specific verb-and-resource pair ("reports where a site's designs are") and enumerates the states returned (planning, designing, done, stopped), which makes the tool's output purpose concrete. It does not contrast itself with siblings like get_design_html or create_designs, so the agent must infer the distinction.

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 is only implied: it is evidently the status/summary read tool, and the sibling names suggest get_design_html is the detail variant, but the description never says when to pick this over that. No exclusions or prerequisites are stated.

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