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

With no annotations, the description carries the full behavioral burden. It does disclose two useful traits: the plan is deterministic (same brief yields the same plan) and it returns a "what to read next" pointer, implying a guided workflow. It says nothing about whether it writes anything, requires auth, has latency limits, or how it fails on an unknown site type.

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?

One dense sentence enumerating the deliverables, followed by a short routing sentence. The purpose is front-loaded and nothing is filler, though the colon-separated output list reads like a compressed manifest rather than 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?

There is no output schema, and the description partially compensates by listing what the plan contains, which is genuinely helpful. Against that, six undocumented enum parameters and no side-effect or prerequisite information leave real gaps for a 9-parameter planning tool.

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 only 33% across 9 parameters: type, needs and style are documented in the schema, but the six enum knobs (cards, rhythm, density, surprise, asymmetry, repetition) have no descriptions anywhere. The description's "from a brief" and mention of "composition direction" hint that those knobs shape the composition, but it adds no per-parameter meaning, so it fails to compensate for the coverage gap.

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?

Names a specific verb (plan) and resource (site) and then enumerates the concrete artifacts returned: recommended noodles, closest template, page outlines with real component ids, composition direction, rules. This clearly distinguishes it from narrower siblings like get_template, find_noodles and get_noodle, which each return a single piece of that plan.

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?

"Start here for any whole website" gives an explicit entry-point condition for the whole-site case, which is the primary routing decision against the other 16 siblings. It does not, however, state a when-not condition or name the alternative to use for partial tasks (e.g. get_component or get_template for a single artifact).

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