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

Annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=true, so the safety profile is covered. The description's collision behavior adds genuine context that reinforces the idempotency claim. But it omits whether the description parameter is applied to a pre-existing collection, visibility, or auth requirements.

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?

A single tight sentence with the core action front-loaded and the edge-case behavior immediately after. No wasted words.

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?

For a two-parameter mutation with strong annotations and no output schema, the definition is adequate but thin. The unaddressed description parameter and the ambiguous return value ('returns the existing one') leave an agent guessing about collision semantics.

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 0%, so the description must compensate and it largely doesn't. It mentions 'name' only through the collision clause, and the optional 'description' parameter is never referenced at all, leaving its purpose and limits unexplained.

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 ('Create an empty collection') and adds a scope qualifier about name collisions. It doesn't explicitly contrast with siblings like list_collections, but the create semantics are unambiguous against the listing/update tools.

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 parenthetical implies when the tool is safe to call (name collisions return the existing collection rather than erroring), which is a useful usage cue. However, there's no explicit guidance on prerequisites, when to prefer update_bookmarks/share_collection, or what happens on failure.

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