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

Beyond the annotations (destructive, idempotent, non-read-only), the description discloses the auth scope required, that the operation is a two-call confirmation protocol, that the first call is a no-op validation, and that unknown fields are refused by name and that the first call returns a summary plus confirm_token. These are exactly the behaviors an agent cannot read off the annotation block and are essential before attempting a destructive mutation.

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, front-loaded with purpose, then permission, then the call count, then the protocol detail. Nothing is repeated from the annotations and nothing is padding, even if the phrasing is telegraphic.

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?

The confirmation protocol and auth requirement are well covered, and the absence of an output schema is offset by naming the first call's return values (summary, confirm_token). However, for a destructiveHint=true operation the description never states what is overwritten (existing order of all mixes vs only the listed ones), and the required `ids` input remains undefined, so an agent could invoke it correctly in flow but not in payload.

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 50%: only confirm_token is described in the schema, and the description largely restates its usage. The sole required parameter, `ids`, is an untyped, undescribed schema entry, and the description never says it is an ordered list of mix ids, whether it is the complete order or a partial reordering, or what ids are valid. For the primary input of a destructive reorder tool, that is a real 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?

"Put my mixes in order" gives a concrete verb (reorder/set order) applied to a concrete resource (mixes), and the two-phase confirm flow further fixes what the operation actually does. It does not explicitly contrast itself with siblings like update_mix or list_mixes, but an agent can infer the distinction without opening the schema.

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 procedural guidance: call once with no confirm_token, show the summary to the person, then call again with the same arguments plus confirm_token only after they agree. It also states the prerequisite permission (content:write). It stops short of saying when to prefer this over update_mix for changing a single mix's position, so it is context-rich but not exhaustive.

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