grade

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 outlines the multi-stage workflow and mentions the 'post-gate' and 'instructor go' requirement, which hints at approvals and side effects. It also references bundled contracts and policies. It does not dive into potential safety issues, permissions, or failure modes, but for a coordinator tool, the disclosed process is fairly 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 long and dense, but every sentence contributes unique information: the global scope, the stage sequence, the bundled artifacts, and the runnable driver. It is front-loaded with the core purpose, though the later sentences become somewhat run-on and list-heavy, making it less crisp than a 5 would require.

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 high complexity as a meta-orchestrator, the description is remarkably complete. It specifies the ordered stages, the bundled policy modules, the engine contracts, and the runnable driver. It also includes the recommendation to invoke before any grading work. An output schema exists, so return value details need not be explained. The high-level runbook is sufficient for an agent to initiate the workflow and know where to find details.

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 input schema has zero parameters, and schema coverage is vacuously 100%. Per calibration, a zero-parameter tool receives a baseline of 4. The description adds no parameter-specific information because there are no parameters to explain, and no further clarification is needed.

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 states a specific verb+resource: it is 'GLOBAL step-by-step grading skill' for 'grading ANY course's Canvas assignment OR quiz/exam through the shared grade engine'. It clearly distinguishes itself from siblings by being the 'ONE ordered procedure' and by naming the bundled components (GRADING.md, SKILL.md, CourseGlobalWorkflow/README.md, GradingEngine/*) and the runnable driver grade_skill.py.

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 says 'Invoke BEFORE any grading work — never grade ad-hoc', which tells the agent when to use this tool. It also describes the full sequence (Stage A → Stage B → report → self-challenge → POST), making the use context clear. However, it does not explicitly name alternative tools or state when not to use it, so it falls short of a 5.

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