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

With all annotations false, the description carries the full burden. It discloses that decisions are 'durably recorded' and that an action with explanation is returned. However, it does not clarify whether the tool actively modifies or stops the generation or merely returns a recommendation for the caller to act on. The side-effect profile beyond recording is ambiguous.

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, front-loaded with purpose and timing, then return values and persistence. Every sentence earns its place with zero filler.

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 7 parameters, nested objects, and no output schema. The description covers purpose, timing, return values, and persistence, which is sufficient for basic invocation. It does not detail the explanation format or error behavior, but given the tight prose, it is largely complete.

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 every parameter has a description. The tool description adds no parameter-specific meaning beyond the schema, so the baseline of 3 applies. It does not clarify how parameters like payload map to the listed actions, but the schema already covers syntax.

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 clearly states the tool's function: 'Quality-govern an in-progress AI generation step BEFORE its output is used.' It uses a specific verb and resource, and distinguishes from the sibling tool validate by contrasting in-progress vs finished documents. The list of returned actions (STOP, CONTINUE, etc.) further clarifies the scope.

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 description explicitly mentions that it 'complements validate, which checks finished documents,' giving a clear when-to-use criterion. It also points to get_inference_trace for later retrieval, implying a usage flow. However, it does not enumerate other alternative tools like repair or reject_rule, so it lacks explicit exclusions.

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