memory.archive

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The description mentions 'preserving canonical documents and revision history,' which implies the archive operation is non-destructive to those elements, but it doesn't clarify what happens to other aspects of the memory (e.g., is it still searchable? does it become read-only? Is there an unarchive operation?). It also gives no indication of side effects or irreversible changes, which is critical for an archive 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, concise sentence that front-loads the core action ('Archive a memory') followed by a key qualifier ('preserving canonical documents and revision history'). It's efficient and to the point, with no redundant words. However, it could be more structured by adding a second sentence with usage guidance, but for its length it earns a high score.

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 a single required parameter and an output schema (which likely describes the result), the description covers the basic purpose well. However, as a mutation-like operation with no annotations, it lacks critical behavioral details (e.g., side effects, reversibility, how the archive differs from deletion). It's minimally complete for an agent to invoke with confidence, but leaves important questions unanswered.

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?

The schema has 0% description coverage, so the description must compensate. It clearly explains the purpose of the single parameter (memory_id) by identifying the target as 'a memory.' It doesn't describe the format (UUID is in the schema) or provide additional semantic context, but since there's only one parameter, the description's mention of 'a memory' is sufficient to clarify what the ID refers to.

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 states a specific verb ('Archive') and a clear resource ('a memory'), and it distinguishes the action by specifying what is preserved ('canonical documents and revision history'). It clearly communicates the primary purpose, even though it doesn't explicitly compare to siblings like memory.propose or memory.delete (which isn't present). It's specific enough for an agent to understand the core intent.

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 implies a specific use case—archiving while preserving canonical data—but provides no explicit when-to-use or when-not-to-use guidance. It doesn't mention when to prefer this over alternatives like memory.propose (new memory) or memory.read (viewing). The phrase 'preserving canonical documents' hints that this is for archiving without destroying key data, but this is not explicit.

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