Update New Quiz Item

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

Annotations already declare idempotentHint=true and destructiveHint=true, so the safety profile is partly covered. The description adds real behavioral context beyond that: Canvas rate-limits rapid sequential updates, calls must be serial rather than parallel, and batches above 50 items need chunking with pauses. It stops short of saying what is destroyed or what auth is needed, capping it at 4.

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 tight sentences, front-loaded with purpose and followed by progressively operational detail. Every sentence earns its place (partial-update note, rate-limit warning, chunking rule). No filler or redundant restatement of the name.

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?

For a complex tool with a five-way polymorphic item payload and no output schema, the description covers purpose, partial-update semantics, and the rate-limit/batching behavior an agent must respect to succeed. It leaves the polymorphic item structure entirely to the schema, which is defensible given the schema's detail, but a note that item shape depends on interaction_type_slug would have closed the remaining gap.

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 83% (high), so the baseline of 3 applies. The description adds one useful semantic note — all fields are optional, supply only what changes — implying partial-update (PATCH-like) semantics. However, that phrasing sits awkwardly against a schema with three required params (course_id, assignment_id, item_id) and gives no guidance on the polymorphic item payload for the five interaction types.

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 with qualifying scope: 'Update an existing item (question) in a New Quiz (LTI).' The '(question)' gloss and 'New Quiz (LTI)' qualifier make it distinguishable from sibling quiz tools (create_new_quiz_item, delete_new_quiz_item). It stops short of naming any alternative explicitly, so it lands at 4 rather than 5.

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?

Provides strong operational guidance (call serially, chunk above 50 items, pause between batches), which tells the agent how to invoke it, but never addresses when to use this tool versus create_new_quiz_item or update_new_quiz. The 'when' is implied by 'update an existing item' only. Adequate but with a clear gap on alternatives.

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