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

The description explicitly states 'Idempotent — re-calling only re-resolves what changed,' but the annotation idempotentHint is false. This is a direct contradiction, making the behavioral guidance misleading. The other behavioral notes (returns summary + per-claim results, owns-claims restriction) are useful, but the contradiction overrides and requires a score of 1.

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?

The description is three sentences and front-loads the purpose. It efficiently packs scope, restrictions, and idempotency with minimal fluff. However, the inaccurate idempotency claim undermines precision, so it loses a point from a perfect score.

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?

The description defines 'due' explicitly with examples, explains scope and restrictions, and notes return values; the output schema covers result details. Yet the idempotency contradiction creates a trust gap, and the description does not clarify whether resolution writes to storage or if there are side effects beyond idempotency. This is adequate but with clear gaps.

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 the schema already documents all three parameters, including the customer_id restriction and defaults. The description adds no new meaning beyond repeating the schema's guidance, so the baseline of 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?

The description clearly states a specific action ('Find every auto-gradable claim that is due') on a specific resource ('claims') with explicit eligibility criteria and a resolution action ('resolve each against fundamentals'). The title 'bulk auto-grader' and the phrase 'caller's OWN claims' differentiate it from sibling tools like score_claim (singular) and score_due_theses.

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?

The description gives clear operational context: it targets the caller's own claims, instructs to omit customer_id, and warns that targeting another user's customer_id is restricted. This implies batch usage for all due claims, but it does not explicitly name alternative tools for single-claim scoring or state when not to use this tool, so it falls short of a full 5.

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