Grades exam essay questions by entering a score and HTML comment for a student response, then syncing both to hidden audit fields in NTHU eeclass.
針對測驗中的人工問答題填入得分與評語（對應 DOM auditEditArea 切換並同步至 hidden textarea[name^=essay_audit]）
| Name | Required | Description | Default |
|---|---|---|---|
| score | Yes | 給予分數（需 <= 該題滿分） | |
| recordId | Yes | 學生作答紀錄 ID | |
| questionId | Yes | 問答題欄位 ID（例如 essay_audit83754） | |
| commentHtml | Yes | 評語 HTML 內容 |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It reveals the write mechanism (DOM auditEditArea switch synced to a hidden textarea) which is genuinely useful context, but it never says what happens on invalid score, whether existing scores/comments are overwritten, what permissions or live Chrome session are required, or how failures surface. For a mutation tool with zero annotation coverage this is a major gap.
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?
One sentence, front-loaded with the action and target. The parenthetical about DOM auditEditArea and the hidden textarea selector is implementation trivia that adds length without helping an agent decide or invoke correctly.
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 write tool with no annotations and no output schema, an agent still lacks information about required session prerequisites, overwrite semantics, and success/failure signaling. The DOM hint implies UI-driven operation but does not make those behaviors explicit.
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 100%, so every parameter is already documented (including the 'score must be <= full marks' constraint). The description adds no per-parameter meaning beyond the schema, 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?
States a specific verb and resource: fill in score and comment for manual essay questions in an exam. It is distinguishable from siblings like audit_homework_submission (homework vs exam) and import_grades_csv (bulk vs single essay). The trailing DOM/textarea implementation detail is noise but does not obscure the 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?
There is no statement of when to use this versus alternatives (e.g., audit_homework_submission, import_grades_csv, ai_assist_grading_feedback) and no preconditions such as session state or exam status. Usage is only inferable from the phrase 'manual essay questions in an exam'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.