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

With no annotations provided, the description carries the full burden and it does disclose the key trait: this tool replaces (overwrites) the person's private soul. It also surfaces a non-obvious behavior—preferences written elsewhere via memory_remember(kind=preference) also absorb into the soul—which agents would not infer from schema alone. It does not cover permissions or irreversibility, but 'replace' already signals the destructive nature.

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 short sentences with no filler: the action is front-loaded, and each subsequent sentence carries distinct information (format preference and preference absorption). This is appropriately sized for a simple two-parameter tool.

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 an output schema exists and the input schema covers 100% of parameters, the description does not need to document return values or parameter details. It covers the core mutation, the preferred body format, and a relevant side effect. The main gap is the lack of routing guidance among the many memory_* siblings, but the purpose is clear enough to invoke correctly.

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 baseline is 3. The description still adds value by specifying a preferred serialization ('compact structured markdown') and by clarifying that preference entries written through memory_remember(kind=preference) are additional content that becomes part of the soul, which is not stated in the schema. The optional agent override is left to the schema, which is sufficient.

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 uses a specific verb ('Replace') with a clear resource ('this person's private soul') and scope ('for the current org'), so an agent can tell this is a write operation on the soul rather than a read. It is more explicit than the title alone, though the domain term 'soul' and the reference 'this person' are not expanded here and are not explicitly contrasted with sibling set tools like memory_agent_set.

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 gives useful how-to guidance: prefer compact structured markdown, and note that memory_remember(kind=preference) preferences absorb into the soul. However, it does not state when this tool should be chosen over alternatives such as memory_soul_get or memory_agent_set, nor does it give any when-not-to-use conditions; usage context is only implied by the replace action.

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