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

Annotations only supply the generic safety profile (readOnlyHint=false, non-idempotent, non-destructive), while the description adds substantial context the annotations cannot: asynchronous background execution (1-3 min), immediate return with a siteId, quota/cost accounting (3 builds/day, up to 5 sites), built-in auth/data/photo features, and the placeholder behavior for missing facts.

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 purpose is front-loaded in the first clause, followed by example, behavior, async model, and cost. All sentences carry information, though the illustrative example sentence is long and the density is high for a single-parameter tool.

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?

Despite an output schema existing, the description still tells the agent the key return value (siteId) and how to poll it, plus the async timing and quota implications. For a background build tool this is exactly the context an agent needs to invoke and follow up correctly.

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?

Only one parameter at 100% schema coverage, so the schema baseline is 3. The description goes beyond it by explaining what belongs in the description string (business + desired functionality), giving a concrete example, and clarifying that real facts become content while missing ones become marked placeholders.

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 ('Builds a new website or simple web app') plus the exact input modality (plain-language business description). The scope and output are distinct from the sibling tools list_sites/get_site/change_site/publish_site, so an agent can tell it apart without opening any 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?

It routes the agent for follow-up ('get_site reports its progress') and surfaces a real selection constraint (costs one of the day's builds). It does not explicitly say when NOT to use it, e.g. that modifying an existing site should go to change_site instead, so the sibling routing is only partial.

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