mark_result

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

The description states the persisted side effect: it accumulates real usage into an eval dataset. This goes beyond the annotations, which only indicate idempotence and non-destructiveness. The note about the usefulness of wrong answers is additional behavioral context that helps the agent decide when and how to call the tool.

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?

The description is compact, front-loaded with the core action, and then adds a practical usage instruction. The 'wrong answer is the more useful judgment' clause is relevant guidance rather than filler. No unnecessary content is present.

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 simple boolean-feedback tool, the description tells an agent what it does, when to invoke it, and what bias of behavior is expected. The annotations cover safety and idempotence, and the schema fully documents the parameters. Nothing essential for correct invocation is missing.

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 input schema has 100% parameter description coverage: query, kbid, and useful are each described. The description adds modest semantic value by explaining that a false answer is still a valuable 'useful' signal, but it does not need to restate the schema. Baseline 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 clearly identifies the action ('Record'), the target resource ('whether a recalled section answered a query'), and the broader purpose ('Accumulates real usage into an eval dataset'). This makes it confidently distinguishable from the retrieval, learning, and search sibling tools, which do not perform feedback recording.

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 gives explicit timing guidance: call it once you know whether a result helped, and explicitly calls out that negative judgments should also be recorded: 'It is wrong answer is the more useful judgment.' It does not enumerate what not to use or name alternative tools, 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.