grade_manually

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

No annotations are provided, so the description carries the full disclosure burden. It does mention useful behaviors (HTML-safe feedback, team grading support, workflow state) but fails to state that this saves/overwrites an existing grade, whether the change is reversible, or what the response looks like. For a mutation tool, this is a significant transparency 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?

The description is three short sentences, front-loaded with the core purpose, and every sentence adds information (operation, HTML-safety, team/workflow features). No redundant or filler content.

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 tool has 7 parameters, no annotations, and no output schema. The description covers some advanced features (team grading, workflow) but omits critical context such as return values, error behavior, permission prerequisites, and the fact that existing grades will be overwritten. Given the tool's complexity, the description is minimally adequate but incomplete.

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 descriptions cover 57% of parameters. The description adds modest meaning by noting feedback text is HTML-safe and mentions team/workflow capabilities, but it does not clarify the three undocumented parameters (assign_id, user_id, feedback_text) beyond what their names suggest. The added context is helpful but not comprehensive enough to raise the score above baseline.

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 action ('Manually grade') and the resource ('an assignment submission'), and references the underlying Moodle function (mod_assign_save_grade) to remove ambiguity. There are no sibling tools that perform grading, so it is well-differentiated.

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 implies the tool is for manual, human-mediated grading but does not explicitly state when to use it versus alternatives (e.g., bulk/automatic grading tools) or provide any exclusion criteria. No other grading tool appears among siblings, but the guidance is still implicit rather than explicit.

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