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

With no annotations, the description must disclose behavior. It reveals the async nature, permission requirement, and default repeats for advanced mode. However, it lacks details on return value, error handling, or state changes, making coverage 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?

The description is brief at two sentences plus a clause, with no unnecessary words. It front-loads the core purpose. However, the third sentence is slightly dense with parentheses, but overall efficient.

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?

With 15 parameters, 1 required, no output schema, and no annotations, the description is too sparse. It fails to explain many parameters, return behavior, or standard mode, making it inadequate for complete understanding.

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 coverage is 0%, so the description must compensate. It only explains mode, baselineVersionId, candidateVersionId, and repeats (defaults). It omits 11 other parameters like artifactBundleId (required), testCases, and maxCases, providing insufficient guidance.

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 'Start an async eval run,' which is a specific verb and resource. It distinguishes this tool from siblings like rubrkit_list_evals or rubrkit_read_eval by indicating it initiates a run asynchronously.

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 provides usage context by requiring evals:run permission and explaining how to use advanced mode with baselineVersionId and candidateVersionId. However, it does not compare standard vs. advanced modes or mention when not to use this tool.

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