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

Annotations already declare destructiveHint=true and idempotentHint=true, so the description's added value is the downstream consequence ('Only approved essays go to Google Classroom') and the explicit reversibility ('The same handles with approve: false reverse approval'). It doesn't explain privileges required or what happens when a handle is already in the target state, but the key side effects are disclosed.

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 primary action, then the selection modes, then the downstream effect and reversal. No filler or repetition of the title.

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 needn't be described. For a mutation tool with partial schema coverage, the description covers purpose, both selection modes, side effects, and reversibility; only edge-case behavior (already-approved handles, permission requirements) 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 description coverage is only 25% (only sessionId and essayHandles items are documented), so the description must carry the rest. It does explain both undocumented booleans: approve: false as the unapprove switch and all: true as the bulk selector, adding meaning beyond the bare schema defaults.

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+resource ('marks scored essays approved') plus the inverse operation, clearly distinguishing it from siblings like override_essay_score or rescore_essay. The parenthetical '(the teacher stands behind the score)' even clarifies the semantic meaning of approval.

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?

Explains the two invocation modes: pass essay handles, or use all: true for every scored essay not yet approved. This is clear operational guidance, though it does not name sibling tools or state when approval is a prerequisite versus optional in the workflow.

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