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

There are no annotations, so the description carries the full behavioral disclosure burden. It discloses that the old memory is marked superseded, stops appearing in search, and that the new memory inherits type, importance, tags, source, and metadata unless overridden. It does not mention reversibility or audit/history behavior, but it is substantially transparent about the mutation semantics.

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 two sentences with no filler. It front-loads the core action and outcome, then efficiently adds inheritance rules and usage guidance. Every sentence earns its place.

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 that this is a mutation tool with no annotations and five parameters, the description covers the essential behavioral context: supersession, inheritance, and when to use the tool. The presence of an output schema reduces the need to describe return values. It could state whether superseded memories remain visible in history, but the current description is adequate for correct invocation.

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 each parameter clearly. The description adds useful context by explaining that tags, metadata, and importance can override inherited values, but it provides no additional syntax or format detail beyond what the schema already covers.

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 a specific action ('Replace a memory with new content') and resource, and distinguishes it from a create/add operation. It also describes the observable outcome: the old memory becomes superseded and stops appearing in search, and the new memory inherits properties. However, it references memra_add, which is not among the listed sibling tools, so differentiation from the actual sibling set is indirect.

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 says to use this instead of memra_add when correcting or updating existing knowledge, which provides actionable selection criteria. It also states it works for all memory types. The main limitation is that it does not contrast with the actual listed siblings like memra_remember or memra_recall, so alternative selection guidance is incomplete.

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