mark_messages_seen

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

Annotations already declare destructiveHint=true, idempotentHint=true, and readOnlyHint=false, so the safety and repeatability profile is covered. The description adds useful context that this mirrors an implicit portal side effect, but it never explains what 'seen' means to recipients or whether the change is reversible, leaving the destructive hint unelaborated.

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 waste; the core action is front-loaded and the clarifying sibling comparison follows. Every clause 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?

No output schema exists and this is a destructive mutation, yet the description omits what happens to the items afterward and whether other users are affected. The portal-behavior analogy partially compensates, but gaps remain for an operation flagged destructive.

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 100%, so all three parameters (origin, message_ids, workspace_id) are already fully documented with sourcing hints. The description adds no parameter-level meaning beyond the schema, so the baseline 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+resource ('Mark feed items as seen') and anchors it to a familiar behavior ('what the portal does when you open the Activity tab'). It also explicitly distinguishes itself from list_messages and get_message, so an agent can tell it apart from read siblings without opening any schema.

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 note that list_messages and get_message 'never do this on their own' strongly signals when this tool is needed (to advance the seen state after reading). However, there is no explicit when-not guidance and no mention of batching or prerequisites such as an active session.

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