forget_memory

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

With no annotations, the description carries the full burden and does so well: it discloses the cascade (KG triples, trigger rows, pin removal with the underlying file archived and its indexed copy deleted), that related memories are demoted, that it reads back to confirm, that an audit trail is logged, and that durable-tier entries need confirm=true. This is exactly the behavioral context needed for an irreversible mutation.

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?

Front-loaded with the core action and its permanence, followed by a dense but informative cascade list and a usage sentence. Every clause carries real information, though the side-effect enumeration is long enough to be slightly heavy for one sentence.

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 destructive multi-effect tool with no annotations and no output schema, the description covers cascade effects, the confirmation gate, and intended usage. It stops short of stating permission-failure behavior or error/return expectations, leaving a small residual gap.

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 the schema already documents memoryId (UUID or 8+ hex prefix), scope, reason, and confirm. The description restates the confirm requirement and audit-trail logging but adds no syntax or format detail beyond the schema; 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?

Names a specific verb+resource (forget a memory) and enumerates the exact cascade of side effects (primary entry, KG triples, trigger rows, pins, demotions). No sibling tool competes for this operation, and the destructive scope is unambiguous.

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?

Explicitly states when to use it: 'when the user explicitly requests a memory be forgotten, or to clean up sensitive/incorrect data,' and adds the confirm=true gate for durable-tier memories. It does not name alternative tools (e.g., demote vs. delete) or when-not to use it, so it falls 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.