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

Annotations only say readOnlyHint=false, idempotentHint=false, destructiveHint=false. The description goes substantially beyond that by disclosing the two-step preview/confirmation flow, what the call actually returns, and that the real state change happens out-of-band by the merchant. This is exactly the kind of behavior an agent cannot infer from structured fields.

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?

Four short sentences with the purpose front-loaded and the critical preview behavior stated plainly. The money/cents sentence is unrelated to any parameter in this schema and reads like carry-over from another tool, which is the one wasted line.

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 mutation tool with no output schema, the description carries the important load: it explains the return (preview plus confirmation link) and why calling it is safe. It would be complete with a note on how edits to an existing category are routed, but nothing essential for calling it correctly is missing.

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 all six parameters (title, handle, parent, imageUrl, isVisible, description) are already documented in the schema. The description adds no parameter meaning at all, and the one detail it does offer ('Money is integer minor units (cents)') refers to a field that does not exist in this tool's schema.

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 sentence 'Add a category' gives a specific verb and resource that separates it from collections_edit and collections_delete by name alone. It does not explicitly name a sibling or scope boundary, but the create-vs-edit distinction is unambiguous.

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?

Usage is implied by the confirmation flow ('Only the merchant, on that page, can make it happen'), which tells the agent this is a request-producing preview rather than a direct write. However, it never states when to reach for collections_edit instead, or any prerequisites such as needing a parent to exist first.

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