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

With no annotations, the description carries the full burden and does well: it discloses that results are typed answers with metered usage and no prose rationale, that a funded account token is required, and that shared state is metered separately per question. These are non-obvious operational facts an agent needs before invoking. It omits failure/error behavior and any rate-limit detail, keeping it at 4.

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?

Four dense sentences, front-loaded with the use case before the mechanics, with no filler. It is packed rather than padded, though the use of the non-obvious term 'noul' alongside compressed clauses makes it slightly harder to parse on first read than an ideal definition.

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 nested-object tool with no output schema and no annotations, the description supplies the essentials: what each question type returns, the metering model, the token requirement, and the no-retrieval constraint. The remaining gaps — error handling, and how this differs from seb_batch_decide — are minor but real.

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 genuine conceptual meaning the schema lacks: choice takes 2–20 option keys mapped to descriptions or null, noul returns a probability in [0,1], and score returns a 0-based expected ordinal over 2–5 ordered levels. Those return-shape semantics are especially valuable because there is no output schema. It does not explain the state parameter's role beyond the schema's own text.

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 states a specific capability — evidence/claim support checks, binary screening, rubric scoring — and enumerates the three question modes (choice, noul, score) it accepts. That is far more than a restatement of the name. It stops short of 5 because it never distinguishes itself from siblings like seb_batch_decide, leaving the agent to guess which entry point handles multi-state or batched work.

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 clear trigger conditions ('evidence/claim support checks, binary screening, rubric scoring') and maps each to a question type, so the agent knows which mode to pick for a given judgment. It also warns 'Include all needed facts; no browsing or retrieval,' which is a real usage constraint. No explicit when-not-to-use or sibling alternative is named, so it falls short of 5.

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