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

Annotations already cover the safety profile (readOnlyHint, openWorldHint), and the description adds real behavioral value by disclosing the return shape: nearest level, exact position, and a per-level probability. No output schema exists, so this return disclosure is the only source for it.

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?

A single front-loaded sentence that states the action, the ordering convention, and the three returned values with zero 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 read-only, three-parameter tool with no output schema, the description adequately covers the return values but omits the role of 'question' and any limits (2–10 levels, 60k character text). An agent can invoke it, but not confidently understand how the question steers the scoring.

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 only 33%, so the description must compensate. It reinforces the levels semantics ('lowest level first'), which duplicates the schema description, but leaves 'question' — the scoring criterion driving the judgment — entirely unexplained in both schema and description.

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 ('place a text on an ordered scale you define') plus the outputs produced, which distinguishes it from binary/choice siblings like judge_yes_no and judge_choice. It stops short of naming those siblings explicitly, so the differentiation is inferable rather than stated.

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?

There is no when-to-use guidance and no routing against the six sibling judge/grade tools. 'A scale you define' implies a custom ordinal use case, but the agent gets no signal about when to pick judge_score over judge_choice or grade_with_rubric.

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