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

Beyond the annotations (destructiveHint, idempotentHint), the description discloses the read-only selection mechanism, the safety rationale (only read rows can be deleted), and the return value (count of deleted items). It even explains the design philosophy of why there is no 'delete everything' tool, which adds significant behavioral context.

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: it states the core action in the first sentence, then explains use cases, safety, and return value. Each sentence adds meaningful information without redundancy. Though somewhat longer than typical, it remains tight and purposeful.

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 tool with an output schema and annotations covering destructive/idempotent behavior, the description covers everything an agent needs: what it deletes, when to use it, the safety guarantee, the return value, and reasoning about alternatives. Nothing essential is missing.

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 has zero parameters, so the schema is empty and provides no ambiguity. Per guidelines, a zero-parameter tool receives a baseline score of 4. The description still reinforces that there are no arguments needed, effectively matching the schema and adding nothing conflicting.

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 tool deletes every notification marked read, with the verb 'delete' and a specific resource. It distinguishes itself from other notification tools by describing itself as a housekeeping call and explicitly contrasting with paging and nonexistent 'delete everything' behavior. It uniquely identifies what it does and why it exists.

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 provides clear context for when to use it ('mark things read first, then sweep') and explicitly warns against using it for unread notifications, emphasizing that it only touches read rows. It mentions alternative approaches like paging, but does not name specific sibling tools like colony_delete_notification. Still, the guidance is concrete and actionable.

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