synthesize_validation

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

The description clarifies the important behavioral distinction that providerResults and question are ignored for review_changes in favor of reloading from the durable run. Annotations already declare readOnlyHint=false and destructiveHint=true, so the safety profile is signaled, but the description does not add detail about what could be destroyed, whether the run creates persistent state, or error behavior.

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 sentences, no filler. The purpose is front-loaded and the mode contrast is in the second sentence. Every clause earns its place.

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 tool has six optional parameters, no output schema, and a destructiveHint=true annotation, yet the description never explains what the synthesized result looks like, what side effects may occur, or how the caller should treat the returned value. The two-mode explanation is helpful but incomplete for safe 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 description coverage is 100%, and individual parameter descriptions are detailed. The description adds contextual framing but no parameter-level details beyond the schema, so the baseline of 3 is appropriate.

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 opens with a clear verb+resource: 'Run an explicit judge model over validation results.' It then distinguishes the two modes and names review_changes as the sibling with different data sourcing. It is slightly jargon-heavy ('explicit judge model', 'owned durable run') but not tautological.

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 second sentence gives explicit usage conditions: general validation uses caller-supplied terminal results, while review_changes rebuilds from the durable run. This effectively tells an agent when each mode applies, though it does not mention other possible alternatives or say when not to call the tool.

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