grade_exercise

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It extensively details side effects and conditions: the wrong-answer flow includes concept_refs and human_note in the receipt, regrading requires explicit regrade: true to avoid CONFLICT, and successful regrading appends previous_score/previous_feedback to a new exercise.graded event. These disclosures go far beyond the schema and provide substantial transparency.

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 dense and covers multiple aspects (trigger, wrong-answer flow, regrade rules, event traces) in three sentences. Every sentence adds substantive value, though the structure is slightly run-on and could be broken into clearer points. It remains informative without being excessive.

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?

Given the tool's complexity and lack of output schema, the description provides a good overview of the main workflows: initial grading after async event, wrong-answer specifics, regrade requirements, and event trace behavior. However, it omits details about the correct-answer path (what happens if score is correct) and the full response structure. Despite these gaps, it covers the most critical aspects for an agent to invoke the 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?

Schema coverage is 60%, with score, regrade, and idempotency_key already documented in the schema. The description adds marginal nuance by mentioning the CONFLICT rejection for regrade without the flag, but does not clarify feedback or submission_id beyond their names. Since the schema already covers most parameter semantics, the description adds minimal additional value.

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: '批改一条 ExerciseSubmission' (grade an ExerciseSubmission), with a specific verb and resource. It also differentiates from siblings by describing the asynchronous trigger (pair://exercises/pending) and the specific grading workflow, which is distinct from other tools like add_exercise or get_submission.

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 usage context: it should be called after receiving the async event pair://exercises/pending, and explicitly explains the regrade workflow (must pass regrade: true for already graded submissions, otherwise CONFLICT). However, it does not explicitly name alternative tools for related tasks, so it falls short of a perfect 5.

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