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

With no annotations, the description carries the full disclosure burden, and it does well: it reveals that the action is attributed to the API key's creator, that it mutates a member's record and is visible to the student, and that revision_requested requires feedback. It omits return-value and idempotency details, but for a mutation tool the disclosed side effects and constraints are substantial.

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 front-loaded, with every sentence earning its place: action, side effects, conditional requirement, and permission. There is no fluff or repetition of schema contents beyond what is useful for behavioral clarity.

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 three-parameter tool with no output schema and no annotations, the description covers the essential calling context: purpose, required status values, visible side effects, attribution, permission, and the feedback requirement. It does not describe the return value or the precise semantics of each status, but these are less critical given the clear enum and mutation focus.

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 id and feedback, and the status enum lists valid values, so the baseline is moderate. The description adds real value beyond the schema by specifying the cross-parameter rule that revision_requested requires feedback, and it clarifies that feedback is instructor feedback shown to the student. This is more than a restatement of properties.

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 opens with a specific verb and resource ('Review an assignment submission') and then enumerates exactly what the tool does: sets a status and instructor feedback. It clearly differentiates this from the read-only siblings like hivelearn_get_assignment_submission and hivelearn_list_assignment_submissions by stating that it changes a member's record and the student will see the change.

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 solid usage context: it is for reviewing/grading a submission, it mutates visible state, and it requires the write:grades permission. It does not explicitly name alternatives or say when not to use it, but the context is strong enough that an agent should know this is the grading action rather than a retrieval tool.

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