list_announcements

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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds meaningful behavior beyond that: it returns a short preview rather than full text, orders results newest first, and includes author/read state. It does not detail pagination or filtering side effects, but the read-only annotation lowers the burden.

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 two sentences with no filler. The first sentence front-loads the output shape and ordering; the second sentence provides the crucial routing to read_announcement. Every sentence 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 what the tool returns and how to get full text, and annotations cover safety. However, it omits the semantics of the optional filters, especially course and unread_only, and does not state whether course null means all courses or a required context. For an agent to invoke it correctly beyond defaults, it must infer too much.

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% and the parameters (course, since_days, unread_only) are only named in the schema with defaults. The description barely compensates: 'Recent' hints at since_days and 'course announcements' hints at course, but it never explains the meaning of course, the time window behavior, or the unread_only filter. This is a significant gap for a 3-parameter tool.

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 states a specific verb 'list' via the tool name and resource: recent course announcements, including exact fields (title, date, author, read state, preview) and ordering (newest first). It explicitly differentiates from the sibling tool read_announcement by noting that full text is available there.

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 explicit routing guidance: 'Use read_announcement with an `id` for the full text.' This tells the agent when to prefer the sibling alternative, satisfying the when-not condition. It also implies the tool is for previews and recent items, which is clear enough for typical use.

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