forget

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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is partly covered. The description adds genuinely new behavior beyond that: omitting confirm yields a free dry-run preview of what would be deleted. It does not say whether deletion is soft or permanent, which keeps it below 5.

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 tight sentences, front-loaded with the verb and resource, then modes, then the confirm/safety rule. Every sentence carries information an agent needs, with no filler.

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 6-param destructive tool with no output schema, the description covers the important cases: both deletion modes, the confirm gate, and the dry-run return behavior. It omits whether deletions are reversible and any permission requirements, so it is not fully complete.

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%, so the baseline is 3, but the description adds real semantic value by showing how parameters combine: ref or category+title for single deletion, category and/or project for bulk. That combination logic is the key thing the flat schema cannot convey on its own.

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 (Remove) and resource (memories), and further splits the operation into single vs bulk modes with their parameter combinations. It is clear and precise, but does not differentiate itself from similarly destructive siblings like memory_prune, memory_purge, or memory_archive, so an agent must still guess which deletion tool to pick.

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?

Gives concrete conditions: single deletion via ref or category+title, bulk via category and/or project scope, and explicitly states that scope deletions require confirm:true while single-target deletions never do. It lacks explicit when-not guidance or routing to sibling deletion tools, keeping it short of a 5.

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