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

Annotations carry only the generic safety profile (readOnly=false, idempotent=false, destructive=false), and the description adds exactly the kind of context annotations cannot: the 409 precondition tied to first settled case, and the version-cap ceiling with its two values and the fact that the error message reports it. This is rich, non-obvious failure-mode disclosure.

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?

Front-loads the core action in the first sentence, then layers the definition and the two constraints. The single dense paragraph with em-dashes is information-rich but a touch packed; every clause still earns its place, so a 4 is fair.

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 create tool with no output schema, the description covers what is created, where it lands (current build-set version), the precondition for success, and the hard limit. Nothing an agent needs in order to call it correctly or interpret common failures 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?

Schema description coverage is 100%, and all three parameters (title, queue_id, description) are documented with lengths and format in the schema itself. The description adds conceptual meaning (Pass/Fail at settlement) but no per-parameter guidance beyond the schema, so the baseline 3 applies.

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?

States a specific verb ("Add") plus a precise resource ("one case-level evaluation rubric to a queue's current rubric set") and explains what a case-level rubric is judged against. An agent can distinguish it from sibling tools like createEvalRubric, replaceCaseQueueEvalRubrics, and updateCaseQueueEvalRubric without opening any schema.

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?

Gives clear situational context: the queue must already have settled an Agent-processed case or this fails with 409, and the version ceiling (12 by default, 25 with the newer generator) determines when additions stop. It does not, however, explicitly route the agent to alternatives like replaceCaseQueueEvalRubrics for bulk replacement, so it earns a 4 rather than 5.

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