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

Annotations already declare idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description goes further by disclosing real behavioral traits: it is asynchronous ('returns immediately with job status'), it has a side effect (generating the rubric first if needed), and its output is staged ('scores remain drafts until teacher approval'). Minor gaps remain (no guidance on duplicate concurrent runs), but this is meaningful context beyond structured fields.

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?

Four short sentences, front-loaded with the core action and then the async, parameter, and approval semantics. Nothing is padded, though the final draft-status sentence could arguably merge with the async sentence.

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 no explanation, and annotations cover safety hints. The description supplies the async/background nature, rubric auto-generation, and draft-approval lifecycle, which is sufficient for an agent to invoke this correctly; only concurrency/duplicate-run behavior is unaddressed.

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 coverage is 67%; sessionId and requestId are already documented in the schema with patterns and sourcing hints. The description adds the one thing the schema omits — that retryFailed controls inclusion of previously failed essays — which is genuine semantic value over the structured data.

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 ('Starts background AI grading for unscored essays on the session's Fiveable rubric') with clear scope. It is readily distinguishable from siblings like rescore_essay, score_submission, or get_grading_progress by the word 'background' and the 'unscored essays' scope.

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 'unscored essays' scope and the 'retryFailed includes previously failed essays' note imply when to use it, but no alternative tool is named and no explicit when-not guidance is given. An agent must infer that get_grading_progress is the polling counterpart and that rescore_essay is for individual re-grades.

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