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

Annotations declare destructiveHint=true and idempotentHint=true, so the agent knows it's a destructive but repeatable write. The description adds that it returns whether the student sees the score yet and how to undo, which is helpful beyond the annotations. However, it doesn't explain the destructiveness beyond 'to undo, set the sections back,' leaving the precise mutation scope unclear.

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 three concise sentences, front-loading the core action and then adding operational details. No fluff, though the last clause about undo is slightly crammed in but still earns its place by hinting at reversibility.

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?

Given the tool's complexity (5 params, destructive write) and the presence of an output schema, the description covers the basic action and undo behavior but omits potential side effects, permission requirements, or how scores interact with grading sessions. It's minimally adequate but leaves gaps for an agent to infer safely.

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?

With 40% schema description coverage, the description doesn't compensate with additional meaning for all parameters. It mentions 'sections' and 'submission item ids' mapping to itemScores.itemId, but doesn't clarify points, itemFeedback, overallFeedback, or their constraints. The schema handles required fields and patterns; the description adds little beyond the core concept.

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+resource: 'Sets the teacher's score on sections of one submission (submission item ids), optionally with written feedback.' This clearly distinguishes it from siblings like override_essay_score and override_submission_part by emphasizing item-level scoring. It doesn't explicitly name those siblings, but the detail about submission item ids is strong enough to avoid confusion.

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?

No explicit guidance on when to use this tool versus alternatives. The phrase 'Works in any scoring mode' implies broad applicability but doesn't tell the agent when to choose score_submission over override_submission_part or override_essay_score. The undo instruction is useful but assumes prior context.

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