prepare_assignment_submission

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, so the agent knows this is a safe read-only operation. The description adds valuable context beyond annotations: it confirms the tool does not upload, describes the return values (course, assignment, group, filenames, hashes, comments), and mentions the intended usage of showing the preview to the student. No contradictions with annotations.

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 two sentences with no redundant words. It front-loads the core action, then adds the critical qualifier 'Does not upload' and the group requirement. Every sentence earns its place, and the structure is scannable for an agent.

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 preview tool with 5 parameters, no output schema, and no nested objects, the description covers the essential points: purpose, the no-upload behavior, group requirement, and return values. It does not mention error conditions or prerequisites like authentication, but those are likely handled by other context. The description is sufficient for an agent to decide when and how to invoke this 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?

Schema description coverage is 60%, with courseId, assignmentId, and groupId already described as 'Exact Brightspace numeric identifier from another tool'. The description adds meaningful context for groupId by noting it is required for group assignments and should come from get_my_groups. However, it does not clarify the format or constraints of files or comments beyond what the schema provides (array of strings, max length). The description partially compensates for the coverage gap but not fully.

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 ('Preview uploading') and the resource ('specific local files to an individual or group file assignment'). It explicitly distinguishes from the confirm step by saying 'Does not upload', which separates it from siblings like confirm_assignment_submission. The scope is precise and unambiguous.

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 a clear condition for when to use this tool: it is for previewing before upload, and it explicitly states the requirement for groupId when dealing with group assignments, referencing the source (get_my_groups). It does not name alternative tools explicitly, but the 'Does not upload' statement implies that the confirm tool is the follow-up. This is adequate guidance, though it could be more explicit about when to choose this over prepare_text_submission.

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