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

Annotations already cover the safety profile (readOnly=false, destructive=false, idempotent=true, openWorld=false), yet the description adds genuinely new behavior: the call also mutates connection state by selecting the new project, and it enumerates the downstream resources that are notably NOT created. What is missing is any explanation of request_key's role in the declared idempotency, which is the one behavioral trait an agent could get wrong on retry.

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, both load-bearing, with the affirmative scope front-loaded and the exclusions second. No filler, no restatement of the title, and it terminates before drifting into schema prose.

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?

An output schema exists so return values need no explanation, and the side effect of selecting the new project is disclosed. But for a tool with a nested creation payload and zero parameter documentation, an agent is still left guessing whether the brief may be populated at creation time and what request_key must contain, which is a real gap at this complexity.

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 description coverage is 0% across a required title, a required request_key, and a 16-field nested brief object, so the description carries the full burden and does not meet it. Worse, "with an empty brief" reads as if the brief argument should be left blank and will not be used, when the schema exposes a full brief object with objective, platforms, language and linkage fields — a mild misdirection rather than added semantics.

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?

Specific verb and resource ("Create one native GenAds project") plus two concrete products of the operation (empty brief, persistent chat). It is distinguishable from the many genads_* sibling tools because it is explicitly the project-creation step rather than media, campaign or ad work, though it never names a sibling like native.create_project or native.link_genads_project to sharpen the boundary.

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 negative scope ("creates no media, advertising account, campaign or advertising approval") tells an agent what not to expect from this call, which is useful routing signal, but there is no explicit when-to-use statement, no prerequisite conditions, and no named alternative for agents who actually want a campaign or media created. Usage is implied rather than prescribed.

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