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

Annotations already declare destructiveHint and idempotentHint, but the description adds a critical behavioral invariant: a partial list is rejected rather than applied, with a rationale. This goes beyond the structured annotations and prevents an agent from assuming a partial update would silently succeed. No contradiction.

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, front-loaded with the core purpose, then a single sentence explaining the crucial constraint. Every clause earns its place, no redundant wording.

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?

Given the simple two-parameter API, full schema coverage, and existing annotations, the description covers the key behavioral caveat. The presence of an output schema means return-value details are not needed. An agent has all necessary information to invoke the tool 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 coverage is 100% — both courseId and orderedScreenIds have descriptions. The description reiterates the 'exactly once' and 'partial list rejected' rules that are already in the array parameter's description, so it adds little beyond the schema. Baseline 3 is appropriate.

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 uses a specific verb 'Sets' and resource 'screen order for a course', clearly identifying the operation. Among sibling tools it is distinct from add_screen, delete_screen, update_screen, and move_course_in_collection, so an agent can distinguish it immediately.

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 description gives clear usage guidance: send every screen id exactly once, and partial lists are rejected. It doesn't name a specific alternative tool, but no close sibling exists; the context of 'sets the screen order' is sufficient for when to use it. The constraint about full list is an important operational guideline.

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