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

Annotations already signal mutation (readOnlyHint=false) and idempotency, so the description's added value is the PREPARING-only constraint and the explicit statement that status cannot be changed. These are meaningful behavioral disclosures, though it doesn't describe failure behavior or whether updates are partial.

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. The core purpose and field list come first, and the critical scope restriction follows immediately. No filler or repetition of the schema.

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 an update tool with no output schema, the description covers the main invocation decision: what can be updated, on which state, and what cannot be done. It is missing minor operational details such as error behavior and success response, but the provided constraints make the tool safely callable.

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?

With 0% schema description coverage, the description carries the parameter burden. It lists the four updatable fields and says 'any of' them can be set, which maps directly to the optional properties and clarifies partial updates. However, it does not define what each field means or any value constraints, so it only partially compensates for the bare 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 description names a concrete action ('Update'), a specific resource ('a draft UT'), and the exact metadata fields affected. It also draws a clear boundary against status changes and non-draft UTs, so it is not confused with create_ut, get_ut, or list_uts.

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?

It explicitly states when the tool applies ('Only works on PREPARING drafts') and when it does not ('cannot change status or edit UTs that are already running or finished'). It does not name a specific alternative tool for status changes or completed UTs, so it stops short of a full 5.

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