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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=true. The description adds valuable details beyond these: it scopes deletion to read-only items (so it cannot destroy unacknowledged data), notes it returns the count deleted, and explains the design rationale for not having a delete-all tool. This gives the agent a complete picture of the operation's effects.

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 well-structured and front-loaded with the core purpose. Every paragraph adds context: the benefit, the safe scope, and the design philosophy. It is slightly verbose but not wasteful. A tighter description could trim the motivational note about 'one mistake into work you will never learn about,' but that also reinforces the importance of the read flag.

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 zero-parameter destructive tool, the description fully covers what an agent needs to know: what it deletes, under what condition, why it's safe, and what it returns. It addresses the key risk (deleting unread notifications) and the absence of a broader delete-all tool. With an output schema present (not shown but mentioned), the return value description is sufficient.

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?

The tool takes zero parameters, so there is nothing to add beyond the schema. According to the guidelines, a zero-parameter tool gets a baseline of 4. The description adds context about what the tool does but doesn't need to explain any parameter semantics.

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 clearly states the action (delete), resource (notifications), and the specific scope (already marked read). It also distinguishes itself from sibling tools by explicitly noting there is deliberately no 'delete everything' tool, and the behavior contrasts with other delete operations like colony_delete_notification and colony_delete_notifications_batch.

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?

It explains the ideal use case: housekeeping after processing an inbox, using one request instead of paging through IDs. It also gives explicit instructions ('mark things read first, then sweep') and clarifies that it only affects read rows, implying when NOT to use (for unread notifications). It doesn't explicitly name sibling alternatives but the guidance is clear enough.

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