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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is partly covered. The description adds substantive context beyond them: the change is logged, the total is recalculated, and reversal restores the previous part points — behavior an agent could not infer from the annotations alone.

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?

Three short sentences, front-loaded with the core action before the logging/recalculation/reversal details. The 'as on the website' clause is slightly informal but does convey parity with the UI behavior; no filler sentences.

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?

An output schema exists, so return values need not be described, and annotations cover the mutation safety profile. The description covers the side effects (logging, recalculation) and reversibility, leaving only auth/permission requirements unstated — a minor gap for this tool.

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 50%, and the description names the key concepts (one rubric part, points, teacher's reason), loosely mapping to three of six params. It adds no format or constraint detail beyond the schema, and says nothing about sessionId, essayHandle, or reasonCategory, so it neither compensates for the coverage gap nor exceeds 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?

States a specific verb (changes/adjusts) and a precise scope (points on one rubric part of a scored essay) plus the reason requirement. It is clearly distinguishable from broad siblings like score_submission or rescore_essay, though it does not explicitly name its closest sibling override_submission_part.

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 phrase 'of a scored essay' implies the tool only applies after an essay has already been scored, which is useful usage context. However, there is no explicit statement of when to prefer this over rescore_essay or override_submission_part, and no prerequisites or exclusions are given.

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