Mark All Announcements Read

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

Annotations already declare this is a non-destructive, idempotent, open-world mutation, so the description's job is narrower. It still adds real context beyond them: the change is per-user read state only, it is bounded by the last N days, and the visible effect is clearing unread badges in Canvas rather than altering the announcements themselves. It omits whether the action can be undone, which is the one gap given no corresponding 'unread' tool exists for announcements.

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 filler; the action and scope come first and the user-visible effect follows. Nothing is repeated or padded.

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 two-parameter batch mutation with clear annotations and no output schema, the essentials are covered. The only omission an agent might want is whether a count of affected announcements is returned and whether read state is reversible.

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% and both parameters already carry descriptions including the 'omit for all active courses' default and the 30-day default. The description restates the same semantics ('last N days', 'all your courses or the ones you pick') without adding format detail such as the 365-day cap or the interaction between days and course_ids.

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?

Uses a specific verb-plus-resource ('Mark every unread announcement ... as read') with explicit scope (last N days, all courses or a chosen subset), which separates it from the single-item mark_announcement_read. It does not name that sibling outright, so the differentiation is inferred from the word 'every' rather than stated.

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 scoping guidance ('across all your courses or the ones you pick') that implies bulk cleanup of unread badges, but it never states when to prefer this over mark_announcement_read or dismiss_global_announcement, nor any exclusions such as course announcements versus global ones.

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