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

Annotations only declare non-read-only and non-destructive; the description adds the meaningful behavioral fact that this is a visible state change ('what puts it in the Exported list') rather than a file-producing operation. It does not cover reversibility (how to un-export), idempotency, or what happens when builder is omitted (that detail lives in the schema), leaving a modest gap for a state-mutating tool.

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 sentences, zero padding, and the core action is front-loaded. The second sentence is a purposeful misconception guard, and the third is an actionable parameter instruction — each sentence earns its place.

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 only two parameters, no output schema, and annotations covering the safety profile, this description supplies everything an agent needs to call it correctly: the effect, the caveat about payload generation, and how to resolve the builder parameter with the user.

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% — builder is documented with an enum while projectId has no description at all. The description compensates on the weak spot that matters most by prescribing the elicitation flow ('ASK the user which page builder... unless they already said, and pass it as builder'), adding process semantics beyond the schema's enum list, though it adds nothing for projectId.

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 ('Mark a project as exported') and immediately defines the concrete effect: it puts the project in the Exported list and is what the WordPress plugin reads. It also explicitly disclaims what it does not do (generate the Elementor/Gutenberg payload), which separates it from export_astro and sync_builders without opening their schemas.

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 a clear when-not ('does NOT generate the payload — the plugin pulls that itself when it syncs'), which is exactly the misconception an agent would otherwise act on, plus a concrete instruction to ask the user for the builder choice before calling. It stops short of naming sibling alternatives (sync_builders, list_exported) explicitly, so routing is implied rather than spelled out.

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