remember

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

With no annotations, the description carries the full burden and does well: it discloses that extraction happens via the current cronista, storage is local, the return includes node id and wall latency, and critically that superseded nodes are retained as history with status=superseded. It omits failure/idempotency behavior and permission or concurrency assumptions.

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?

Short, front-loaded, and each line earns its place: what it produces, how relations and supersedes work. The internal benchmark reference is slightly extraneous but harmless context for the returned latency.

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 five-parameter mutation with no annotations and no output schema, the description covers the core write and supersede mechanics but leaves two parameters undefined and says nothing about error or duplicate handling. Adequate, not complete.

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 coverage is 0%, so the description must compensate. It explains the two hardest parameters well ('relations' shape with an example, 'supersedes' chain semantics including auto-supersede), but 'tags' and 'session' are documented nowhere in either the schema or the description.

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+resource pair ('Turn ... text into a MemoryNode') and enumerates the internal steps: extract narrative structure, store locally, return the node id. Against siblings recall/forget/get_node/stats it is clearly the write path, though it never names a sibling to contrast with.

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?

Usage is implied by the mechanics rather than stated: it explains when to supply 'relations' and 'supersedes', but gives no explicit 'use this instead of recall when...' routing or prerequisites. An agent can infer this is the ingestion tool, but must infer it.

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