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

The description adds behavioral details beyond the annotation (destructiveHint: false), such as 'unanswered questions score as incorrect' and the return composition ('scaled score, PASS/FAIL vs the pass line, a per-domain breakdown, and the per-question rationale'). It also states an evaluative behavior ('Deliver it as an honest scorecard and point them to the weak domains' modules'). No contradictions with annotations.

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, each adding distinct value: what it does, how answers map, and what it returns plus a delivery guideline. No redundant phrasing, and the main action is front-loaded in the first sentence. It is appropriately sized without being verbose.

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 covers prerequisites ('started with start_exam'), the input format, the scoring rule for unanswered questions, and the output components. However, it does not clarify how the specific exam attempt is identified (e.g., via `course` or if there is an implicit attempt reference), which is a notable ambiguity for a submission tool. Despite this, the presence of an output schema reduces the burden of explaining return values, so the description is largely complete.

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 0%, so the description must compensate. It thoroughly explains the `answers` parameter with a concrete example ('{"q001": "A", "q002": "C"}') and the rule for unanswered questions. It does not explain `course` or `auth_token`, but the latter is self-evident and `course` is a common identifier. The explanation of the most complex parameter is strong, so this earns a 4 rather than a 3.

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 the tool's function: 'Score a practice exam started with start_exam.' This specifies a concrete verb ('score') and resource ('practice exam'), and explicitly differentiates it from the sibling tool start_exam by pairing with it. The title 'Submit exam answers and score the attempt' reinforces this purpose.

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 provides clear context for when to use the tool: 'Score a practice exam started with start_exam.' This implicitly conveys that it should be used after start_exam and is the scoring counterpart in the workflow. However, it does not explicitly state when not to use it or mention alternatives (though there are none evident among siblings), so it misses the top score.

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