get_grading_rubric

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It discloses that the tool bundles all necessary grading materials in one call, is meant for qualitative formative feedback, and intentionally does not return a hard score. It does not mention side effects or error behavior, but for a read-only resource tool this is reasonably transparent.

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 but front-loaded: it announces the resource type and call timing before listing contents. The long single sentence with emojis and slash-separated items is compact and mostly earns its place, though clearer line breaks would improve scannability.

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?

With no output schema and no annotations, the description carries the burden of explaining return value and behavior. It lists the major rubric components, the intended grading use, and the 'no hard score' constraint. It does not describe the exact return structure or how to obtain qid, but it is sufficiently complete for an agent to select and 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?

The single required parameter qid has 0% schema coverage, and the description never explicitly defines qid or its format. It only refers indirectly to '該題' (that question), which implies qid is the essay question identifier. This adds some meaning beyond the bare schema but does not fully compensate for the missing parameter documentation.

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 identifies the tool as an essay-grading rubric ('申論批改評分表') and specifies exactly what it returns: issue checklist, doctrine conflicts, case citations, recognition signals, model answer, and five-dimension criteria. It also distinguishes itself from simple answer retrieval by framing the output as formative feedback material and explicitly noting it does not produce a hard score ('不打硬分數').

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 an explicit trigger condition: call after the student completes an essay answer ('學生寫完申論作答後呼叫'), and states the purpose is point-by-point formative feedback on missed issues, incomplete elements, etc. It does not name alternative sibling tools or explicitly say when not to use other tools, 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.