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

Annotations already declare destructiveHint=true, idempotentHint=true, and readOnlyHint=false, so the safety and idempotency profile is covered. The description's 'changes existing timeline state' and 'retry-safe receipt' largely restate those hints, adding only modest output context on top of the existing output schema.

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?

Two tight sentences with the resource and revision constraint front-loaded and no filler. It is appropriately sized, though the second sentence is close to restating the destructive and idempotent annotations.

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?

A mutation tool with full annotation coverage and an output schema needs less prose, and the description does convey the state change and revision guard. However, it leaves out what happens on a revision mismatch and how splitAtSeconds/snapToFrame interact, which are material 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?

Schema coverage is only 33%, so the schema does not carry the load. The description names the item and the revision expectation, which maps to timelineItemId and expectedRevision, but splitAtSeconds, snapToFrame, and idempotencyKey semantics are not clarified beyond their type definitions.

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 ('Split one timeline item') with an explicit scoping constraint ('at the expected project revision'), so the agent can distinguish it from the many other timeline mutators. It never names timeline_split_preview as the read-only counterpart, so sibling differentiation is left to inference.

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 apply-vs-preview sibling pairing and by the requirement of an expectedRevision, but the description never states when to call this instead of timeline_split_preview or what to do when the revision is stale. No exclusions or preconditions are given.

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