whats_new

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

The description discloses a non-obvious stateful behavior: the tool remembers the last call time and uses it as the default window, and that passing `since` does not update that marker. This goes well beyond the readOnlyHint and openWorldHint annotations, which only indicate safety and that results may vary. The description also clarifies the first-time fallback, which is exactly the kind of behavioral context an agent needs.

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?

The description is compact and front-loaded: the first sentence states the purpose, the second explains the default behavior, and the Args section is terse and scannable. Every sentence earns its place, and the parameter documentation is formatted for quick parsing.

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 is complete for a read-only, two-parameter tool with an output schema present. It explains the stateful default, the parameter semantics, and the scope of results. The only thing not covered is the exact shape of the output, but the output schema exists and the description doesn't need to duplicate it. A small gap is that it doesn't mention whether results are sorted or limited, but that's minor given the output schema.

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 0%, so the description carries the full burden for parameter meaning. It does this well: `since` gets format examples and the semantic distinction of not moving the marker, and `course` gets accepted formats (code, id, or name) with an example. The only minor gap is that it doesn't specify what happens if an invalid course is provided, but that's not essential for invoking the tool correctly.

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 opens with a specific verb ('what changed') and enumerates the exact resource types covered: new or edited items and files, new grades, new forum posts. This clearly distinguishes it from siblings like announcements, grades, or read_discussion, which focus on single resource types.

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 explicitly explains the default time window behavior and how the 'last check' marker works, including the first-call fallback of 7 days. It also documents the two optional parameters with concrete examples ('3d', '12h', '2w', or a date like '2026-09-20'), and clarifies that using `since` does not move the marker. This is strong when-to-use guidance.

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