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

Annotations already flag destructiveHint=true, readOnlyHint=false and idempotentHint=false, but the description adds what the annotations cannot: existing rubrics are removed and replaced, why an empty list is rejected (regeneration at settlement), and that already-judged cases keep their verdicts. This is rich, non-duplicative behavioral context.

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-loaded with the core action, then the destructive consequence, then the empty-list caveat, then the version precondition. Every sentence carries a distinct piece of operational information; none is 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?

For a destructive mutation tool with no output schema, the description covers the mutation semantics, failure modes (409, empty-list refusal), limits, and side effects on already-judged cases. Nothing an agent needs to call it safely 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 coverage is 100% and both parameters are documented in the schema, so much of the value is already structured. The description nevertheless adds meaning beyond the schema: the effective rubric count range (1 to 12 by default, 25 with the newer generator) and the semantics of 'empty list' for the rubrics array.

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 and resource: replacing the entire case-level rubric set on a queue's current version. The scope ('entire set', 'current version / build-set') clearly separates it from the sibling create/update/delete single-rubric tools and from replaceEvalRubrics at the non-case level.

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?

It gives the when-to-use (whole-set replacement), an explicit when-not with an alternative action ('An empty list is refused... remove individual rubrics instead'), and a precondition for use ('fails with 409 before its first Agent-processed case settles'). Routing is fully inferable without opening another schema.

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