grade_submission

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

With no annotations provided, the description carries full responsibility for exposing side effects, and it does so well. It explicitly warns 'WRITES TO MOODLE, visible to the student,' notes that the grade uses the assignment's own scale, and states 'This overwrites whatever mark and comment were there before.' This gives the agent the critical destructive-mutation context.

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 compact and well-structured: the mutation warning is front-loaded in ALL CAPS, followed by the core action, then key behavior detailscherry, and finally a user-confirmation directive. Every sentence adds necessary operational or risk information without filler.

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 six-parameter mutation tool with no output schema, this description is complete enough for an agent to invoke it correctly. It covers the primary parameters (grade, feedback), the special -1 sentinel value, the overwrite side effect, student visibility, and the need for user confirmation. It also cross-references assignments for scale context.

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 schema already documents all six parameters with full coverage, so the baseline is 3. The description adds meaningful value by explaining that the grade is on the assignment's own scale, that -1 leaves the mark unchanged, and that feedback overwrites prior comments. This goes beyond the schema's per-parameter descriptions, though it does not add detail for every parameter.

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 uses a clear verb-resource pairing: it 'Put[s] a mark and written feedback on one submission' and explicitly says it 'WRITES TO MOODLE, visible to the student.' This distinguishes it well from sibling listing/inspection tools like submissions, submission_status, and gradebook.

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 context for when to use the tool: grading a single submission with a mark and feedback. It also adds the practical guardrail to 'confirm the numbers with the user first.' However, it does not explicitly name alternative tools or state when not to use this tool instead of gradebook or other related functions.

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