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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and a closed world, so the safety profile is fully covered. The description does add real semantics beyond that: "Scores marked AI draft aren't approved yet," which tells the agent how to read status values. It does not mention pagination or result-size behavior.

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?

It is front-loaded with the output inventory, which is good, but that inventory substantially duplicates the existing output schema and consumes most of the text. The trailing filter fragment is choppy and the draft/approval note is buried at the end rather than structured with the filter it modifies.

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?

Because an output schema exists, the long return-value inventory is redundant rather than necessary. What is actually missing is routing (when to use this vs export_grading_results or list_submissions_to_review) and paging behavior, so the agent can call it but has weak guidance on choosing it.

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 only 25% (sessionId alone is documented). The description's filter phrasing merely restates enum values already present in the schema and adds nothing for offset or limit, whose paging semantics are the least self-evident of the three undocumented parameters. With low coverage and no compensating detail, it falls below the 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?

It names a specific resource (class results for a grading session) and enumerates the payload: average, distribution, rubric-part breakdown, gaps, and an essay table. That clearly separates it from a single-essay tool, but no sibling is named, so the agent must infer the boundary against get_grading_progress, export_grading_results, or list_submissions_to_review.

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?

"Filter to the ones that need review, drafts, approved or failed" describes parameter values, not when to reach for this tool over its siblings. There is no stated precondition (e.g. a completed session) and no mention of export_grading_results or get_grading_progress as alternatives.

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