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

Annotations already mark the tool as read-only, idempotent, and non-destructive, and the description reinforces this with 'safely check' and 'never unfinished scores or feedback.' It adds valuable edge-case transparency around pending/partial grading and the honors practice reset limitation, going well beyond what the annotations alone provide.

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?

Two tightly packed sentences front-load the core operation before addressing edge cases. Every clause adds meaningful information, with no repetition of the title and no 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?

The description covers invocation modes, identifier constraints, result availability behavior, and the honors-practice limitation. Combined with the existing output schema and read-only/idempotent annotations, an agent has everything needed to invoke this tool correctly.

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?

With 0% schema description coverage, the description carries the full semantic burden and succeeds: it explains when to use attemptId versus submissionId and enforces the mutual exclusivity rule with 'Supply exactly one.' It also conveys the ownership condition ('owned completed exam') that the raw schema cannot express.

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 opens with a specific verb 'Read' and clearly scopes the tool to 'an owned completed exam' via attemptId or 'a submitted exam' via submissionId, establishing two distinct invocation modes. It also adds non-obvious behavioral details about pending/partial grading and honors practice, which further defines what the tool does and does not return.

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 explicitly instructs the agent to supply exactly one identifier and maps each parameter to its appropriate scenario: attemptId for owned completed exams and submissionId for submitted exams. It also warns that pending or partial grading returns status only, preventing unrealistic expectations. It does not name alternative sibling tools, but the usage context is clear.

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