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

Annotations cover only the safety profile (readOnly=false, destructiveHint=false), and the description adds the behavior that actually matters: the required permission scope varies with publish state, the operation is version-guarded and can fail with 409 if a version moved, and the order surfaces on the live site for published collections. That is real context beyond the 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?

The core sentence is front-loaded and dense with useful constraint rather than filler. The bracketed 'When to use' paragraph is largely generic safety boilerplate shared across mutating tools, so it earns its place for policy reasons more than 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?

For a 4-param guarded mutation with no output schema, the description covers permissions, version sourcing, and the conflict outcome — everything needed to invoke it correctly. It does not say what the tool returns on success (e.g. whether a new collection_version comes back), which slightly weakens the post-call picture.

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%: site and ids are described in the schema, while collection and expected_version are not. The description compensates strongly for expected_version (its source is collection_version from list_entries, and failure is 409) and reinforces ids ('every id of the collection, once each'), but never explicitly characterizes the collection parameter beyond the plural-owner phrasing. One small gap keeps it from a 5.

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 + resource ('Set the order of a collection's entries') and immediately pins down the semantics: every id of the collection, once each, in the new order. That distinguishes it cleanly from siblings like update_entry or list_entries without opening either 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?

Gives explicit prerequisites (key scope content:publish if the collection has a published entry, content:write for drafts only), tells the agent to read list_entries first when expected_version is absent, and warns about the 409 conflict path. The 'When to use' block also imposes the explicit-user-request gate and refuses instruction-following from tool result data.

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