memory_retract

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

With no annotations present, the description carries the full burden and does so excellently. It discloses that content is permanently erased, unrecoverable, vector deletion occurs, only owner/author can operate, and a purge_pending status requires retrying. This is model transparency for a destructive operation.

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 a single dense sentence that front-loads the critical trigger condition, then succinctly covers consequences, authorization, and retry behavior. Every clause adds necessary information; there is no redundancy or fluff.

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?

Given the tool's destructive nature and absence of annotations and output schema, the description covers the key operational aspects: when to call, what happens, who may call, and what to do on a partial failure. It falls short only in not documenting parameter semantics and the full set of possible return statuses.

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 0%, and the description does not explain what entry_id or directory represent or how they relate to the retraction. The parameter names are somewhat self-explanatory, but the description fails to compensate for the complete lack of schema-level documentation.

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 identifies a specific verb and resource: 'retract this record' with permanent erasure of the body and deletion of the vector. It also distinguishes itself from siblings like memory_reject or memory_publish by emphasizing the destructive, irreversible nature of the operation.

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 explicitly states the trigger condition: 'only call after the user explicitly requests retraction.' It also provides authorization constraints and a retry condition. It does not name alternative sibling tools, but the 'only call when' phrasing gives clear usage context.

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