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

Annotations only declare the generic safety profile (not read-only, not destructive, not open-world), so the description carries real weight and delivers: it discloses that the call is one-shot ('ONCE'), must precede first-page generation, and that skipping it causes drift to generic output. It stops short of saying whether a second call overwrites an existing direction or what the applied state looks like afterward, which keeps it off a 5.

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 ordering constraint is front-loaded before the parameter guidance. Every clause carries actionable information — timing, selection preference, and exclusion.

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 and no required parameters, the description supplies everything the agent needs: when to fire, what it mutates, the precondition that makes it necessary, and the choice between the two input shapes. Nothing material is left to inference for a tool whose only real risk is calling it at the wrong time.

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 100%, so the baseline is 3, but the description adds a genuine decision rule the schema does not: use directionId unless the brief calls for something the menu cannot cover, then author custom fields. That resolves the mutual-exclusivity question the schema leaves implicit, which is real added value on top of the nested object's own docs.

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 ('Commit this site to a specific visual direction') plus the concrete side effects ('apply it (fonts, type roles, palette swatches)'). No sibling tool touches visual direction, so an agent can immediately distinguish it from create_site, create_page, or update_settings.

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 explicit timing ('Call this ONCE, BEFORE generating a new site's first page'), an explicit negative case ('Not needed when editing a site that already has a direction'), and a routing rule between the two input paths ('Prefer a directionId from the sampled menu; supply the custom fields only when...'). This is exactly the when/when-not/alternative guidance the dimension asks for.

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