word_live_repair

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

With no annotations, the description carries the full burden and does well: it discloses the mechanism ('fresh attach'), the three concrete effects, the safety profile, and that it reports what was fixed. It could add what side effects a fresh attach might have on unsaved document state, but it is materially transparent.

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, front-loaded with 'Recovery tool,' then the condition, the fixes, and the report behavior. Every word earns its place and nothing is redundant.

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 no-parameter repair tool with an output schema, the description covers the purpose, when to run it, what it fixes, safety, and reporting. There is no missing information an agent needs to decide to invoke it.

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?

The tool has zero parameters, so the description does not need to document any. Baseline 4 applies because there is no parameter surface for it to clarify or compensate for.

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 uses a specific recovery verb and names the exact resource and failure modes: a crashed live edit leaving Word frozen, alerts suppressed, or an undo record open. It clearly distinguishes this as a repair tool rather than a general document or live-edit tool.

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 states the triggering condition ('if a crashed live edit left...') and explicitly says 'Safe to run anytime.' It does not name alternatives or exclusions, but the recovery condition and broad safety guidance give clear usage context for a 0-parameter tool.

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