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

Annotations already flag destructiveHint=true and non-idempotent, so safety is covered. The description adds real behavioral context beyond that: existing custom rubrics are removed and fully replaced, a default cap of 5 rubrics (25 with the newer generator), and the empty-array clearing behavior. It omits permission/auth requirements, but the destruction semantics are unusually well disclosed.

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?

Three dense sentences, front-loaded with the core replace action and limits; every clause carries information (caps, clearing, default target). The opening sentence is long but not padded.

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, non-idempotent mutation with no output schema, the description covers scope, replacement semantics, cardinality limits, and the target-build default. The remaining gap is failure/permission behavior, which is minor given annotations already declare the destructive profile.

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%, so the baseline is 3, but the description contributes meaning not in the schema: the default cap of 5 rubrics (schema only shows maxItems 25) and the explicit note that build_id targets a specific revision versus the live build default. That extra constraint raises it above baseline.

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 (Replace) and resource (a build's entire Agent-specific evaluation rubric set), and scopes it clearly to the build level, which separates it from siblings like replaceCaseQueueEvalRubrics, createEvalRubric, and updateEvalRubric. An agent can identify the operation and its replace-semantics without opening the 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 concrete conditions: defaults to the Agent's live build unless build_id is passed, and an empty array clears the set. However, it never explicitly routes the agent away from the singular siblings (createEvalRubric / updateEvalRubric / deleteEvalRubric) when only one rubric changes, so the when-not guidance is inferred rather than stated.

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