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

Annotations provide only false/non-informative hints, so the description carries the full burden. It discloses meaningful behavioral detail: rubrics attach to the current version/build-set, the 409 precondition, and the 12-rubric cap. This is exactly the kind of context an agent needs beyond the schema.

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 first sentence front-loads the core purpose, and the second sentence earns its place by defining case-level evaluation. The third sentence is dense, packing versioning, the 409 condition, and the 12-rubric limit into one clause, but it remains informative and reasonably sized for the complexity.

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?

Given no output schema and non-informative annotations, the description gives enough context to invoke the tool correctly: the target version, the prerequisite, the failure mode, and the maximum rubric count. The only minor weakness is the slightly ambiguous phrasing around the 12-rubric condition, but it does not block correct use.

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 100%, so the baseline is 3, but the description adds semantic value beyond the schema by explaining that rubrics are Pass/Fail questions evaluated at settlement across the whole case. This helps the agent understand what the title and description parameters should contain, even though the schema already documents their basic format.

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 specific verb and resource: 'Add one case-level evaluation rubric to a queue's current rubric set.' It clarifies what makes this rubric distinct ('judge the whole case across every Run that touched it') and distinguishes it from siblings like createEvalRubric and replaceCaseQueueEvalRubrics.

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 clear usage context: this adds a single rubric to the current build-set, only works after the first Agent-processed case settles, and fails with 409 before then. It does not explicitly name alternative tools such as replaceCaseQueueEvalRubrics, but the additive scope and constraints make the intended use reasonably clear.

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