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

Annotations already establish it is a non-read-only, non-destructive, idempotent write. The description adds a real behavioral constraint beyond them: the operation only affects failed scoring and leaves successful scores untouched. It does not say what happens (error vs. no-op) if invoked on an already-scored essay, which is the remaining gap.

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?

Two sentences, zero filler, with the retry action front-loaded and the scope limitation immediately after. Nothing repeats the title or schema.

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?

With an output schema present, return values need no explanation, and all three parameters are documented in the schema. The description supplies the failure-retry framing and the non-mutating-of-successful-scores constraint, which is everything needed to call it 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 100% with all three required parameters fully documented, including patterns and provenance for sessionId and essayHandle. The description contributes no additional parameter meaning, so the baseline of 3 applies.

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 and resource ('Retries background AI grading for one essay'), and the qualifier 'whose scoring failed' plus the scoping sentence implicitly carve it out from the score-changing sibling override_essay_score. It stops short of naming that alternative explicitly, so an agent must infer the boundary.

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?

'for one essay whose scoring failed' gives a clear triggering condition, and 'Existing successful scores cannot be changed by this operation' supplies a when-not condition. No sibling is named as the alternative for the case the exclusion rules out, so the guidance is clear but not fully routed.

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