Mark Announcement Read

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

Annotations already declare not-read-only, idempotent, non-destructive, and open-world. The description adds the one piece of behavior annotations cannot express: the effect is 'clearing its unread badge'. It says nothing about the already-read case, permission requirements, or what is returned, so it clears the annotation bar without going much beyond it.

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?

One short sentence with the scope constraint and the observable effect front-loaded, and zero redundant wording. Nothing in it could be cut without losing meaning.

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, single-item mutation with full schema coverage, four annotations, and no output schema, this is nearly sufficient. The only shortfall is not pointing at the sibling bulk tool or listing where IDs come from, both of which the schema partly handles.

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 the schema itself explains both course_id (from list_courses) and announcement_id (from list_announcements). The description adds no supplementary parameter meaning, so the baseline of 3 applies.

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 (mark ... announcement as read) plus the scope qualifier 'one course announcement', which implicitly separates it from the bulk sibling mark_all_announcements_read. It stops short of naming that sibling, so an agent still has to infer the routing.

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 word 'one' implies single-item usage versus the bulk variant, but there is no explicit when-to-use/when-not guidance, no mention of mark_all_announcements_read, and no note about list_announcements being the source of the ID. Usage is inferred rather than stated.

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