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

Annotations already declare idempotentHint=true and readOnlyHint=false. The description adds 'self-reported planning' and 'retry identical input safely', which align with idempotency and provide context beyond the annotations. It does not contradict annotations, and the added context is valuable.

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 with no fluff. The central action and key constraints are front-loaded, and every phrase earns its place.

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?

The description covers purpose, usage exclusions, and key parameter semantics. With an output schema and annotations handling safety and idempotency, it is sufficiently complete. It doesn't mention error handling or prerequisites, but those are not essential given the other structured fields.

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 only 25% (only requestId has a description). The description adds meaning to expectedRevision ('Supply the latest revision') and reinforces requestId's uniqueness, but it does not explicitly describe tasks or planId. These are inferable from names and schema patterns, but the description could compensate more given the low coverage.

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 clearly states a specific verb (marks) and resource (owned plan tasks) and explicitly differentiates from quiz/practice submissions. This distinguishes it from sibling tools that handle scoring. The phrase 'at the student's request' adds context without ambiguity.

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?

It provides a when-not ('never a quiz score or practice submission') and a when ('at the student's request'), but does not name alternatives or explicitly say when to prefer this tool over others. With no direct update sibling, the lack of alternatives is acceptable, but the guidance is partial.

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