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

The description reveals a non-obvious behavioral quirk: the response may have visible_on_splitpage=false, and the collection will not render until it is patched to true. It also explains how smart collections auto-include matching links. Since annotations only state readOnlyHint=false (no other detail), this description carries the full burden and excels.

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 description is three sentences, front-loaded with the core purpose and required fields. It packs essential details (section-first requirement, smart vs. regular, visible_on_splitpage check) without redundancy. Some verbose phrasing could be tightened, but it's efficient for the information density.

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?

Given the tool's complexity (8 parameters, two collection kinds, a hidden rendering pitfall), the description covers the most critical guidance: required fields, ordering, query semantics, link limitations, and the visible_on_splitpage caveat. It omits optional image_params and image_upload_id, but those have schema descriptions and are not essential for correct invocation.

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?

While the schema already covers 75% of parameters with descriptions, the tool description adds semantic depth: it explains that `query` may be {} and gives useful keys (tags, q, domains, sort), and clarifies that `link_uuids` only works at creation. This compensates for the remaining 25% of undocumented parameters (e.g., image_params) without repeating schema content.

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?

The opening phrase 'Create a collection' is a specific verb+resource that clearly states the tool's purpose. It further distinguishes between smart and regular collections, and the requirement to create a section first sets it apart from sibling tools like split_create_section or split_update_collection.

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 description gives explicit prerequisites (create the section first) and clarifies when link_uuids can be used ('only works at creation time'), which implies that later modifications go through split_update_collection (also noted in the schema). It does not state 'use split_update_collection for edits' explicitly out loud, but the guidance is clear enough.

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