Mark Conversation Unread

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

Annotations already declare this is a non-destructive, non-read-only mutation with openWorldHint=true. The description adds real blast-radius context beyond them: 'Only affects you' tells the agent other participants are unaffected and no notification is emitted, which annotations cannot express.

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?

Three short sentences, front-loaded with the action and its effect, then scope, then the inverse tool. No filler or redundancy.

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 one-parameter mutation with full annotations and no output schema, the description covers what it does, who it affects, and how to undo it. The only gap is any note on whether the call errors for an already-unread conversation, given idempotentHint=false.

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 single parameter's description already covers type and provenance ('Get it from list_conversations'). The description adds nothing about the conversation_id, 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 (mark unread) and resource (one Inbox conversation), and adds the observable effect 'so it shows up again'. The word 'one' distinguishes it from sibling bulk operations like batch_update_conversations and mark_all_entries_read without needing the 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?

Names the inverse operation explicitly ('Reverse with mark_conversation_read'), giving the agent a clear routing rule and undo path. It does not address when to prefer batch_update_conversations for multiple conversations, but the singular scope is implied by 'one'.

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